1
|
van Dyck LE, Bremmer F, Dobs K. Artificial intelligence meets body sense: task-driven neural networks reveal computational principles of the proprioceptive pathway. Signal Transduct Target Ther 2024; 9:171. [PMID: 38972921 PMCID: PMC11228032 DOI: 10.1038/s41392-024-01870-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2024] [Revised: 05/02/2024] [Accepted: 05/07/2024] [Indexed: 07/09/2024] Open
Affiliation(s)
- Leonard E van Dyck
- Department of Psychology, Justus Liebig University Giessen, Giessen, Germany.
- Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany.
| | - Frank Bremmer
- Center for Mind, Brain and Behavior, Universities of Marburg, Giessen, and Darmstadt, Marburg, Germany
- Department of Neurophysics, Philipps-Universität Marburg, Marburg, Germany
| | - Katharina Dobs
- Department of Psychology, Justus Liebig University Giessen, Giessen, Germany.
- Center for Mind, Brain and Behavior, Universities of Marburg, Giessen, and Darmstadt, Marburg, Germany.
| |
Collapse
|
2
|
Ma W, Li M, Dai J, Ding J, Chu Z, Chen H. Nutrition-Related Knowledge Graph Neural Network for Food Recommendation. Foods 2024; 13:2144. [PMID: 38998649 PMCID: PMC11241430 DOI: 10.3390/foods13132144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2024] [Revised: 07/01/2024] [Accepted: 07/04/2024] [Indexed: 07/14/2024] Open
Abstract
Food recommendation systems are becoming increasingly vital in modern society, given the fast-paced lifestyle and diverse dietary habits. Existing research and implemented solutions often rely on user preferences and past behaviors for recommendations, which poses significant issues. Firstly, this approach inadequately considers the nutritional content of foods, potentially leading to recommendations that are overly homogeneous and lacking in diversity. Secondly, it may result in repetitive suggestions of the same types of foods, thereby encouraging users to develop unhealthy dietary habits that could adversely affect their overall health. To address this issue, we introduce a novel nutrition-related knowledge graph (NRKG) method based on graph convolutional networks (GCNs). This method not only enhances users' ability to select appropriate foods but also encourages the development of healthy eating habits, thereby contributing to overall public health. The NRKG method comprises two key components: user nutrition-related food preferences and recipe nutrition components. The first component gathers nutritional information from recipes that users show interest in and synthesizes these data for user reference. The second component connects recipes with similar nutritional profiles, forming a complex heterogeneous graph structure. By learning from this graph, the NRKG method integrates user preferences with nutritional data, resulting in more accurate and personalized food recommendations. We evaluated the NRKG method against six baseline methods using real-world food datasets. In the 100% dataset, the five metrics exceeded the performance of the best baseline method by 2.8%, 5.9%, 1.5%, 9.7%, and 6.0%, respectively. The results indicate that our NRKG method significantly outperforms the baseline methods, including FeaStNet, DeepGCN, GraphSAGE, GAT, UniMP, and GATv2, demonstrating its superiority and effectiveness in promoting healthier and more diverse eating habits. Unlike these baseline methods, which primarily focus on hierarchical information propagation, our NRKG method offers a more comprehensive approach by integrating the nutritional information of recipes with user preferences.
Collapse
Affiliation(s)
- Wenming Ma
- School of Computer and Control Engineering, Yantai University, Yantai 264005, China
| | - Mingqi Li
- School of Computer and Control Engineering, Yantai University, Yantai 264005, China
| | - Jian Dai
- Xinjiang Academy of Agricultural Sciences, Urumqi 830091, China
| | - Jianguo Ding
- Institute of Agricultural Economics and Information, Xinjiang Academy of Agricultural Sciences, Urumqi 830091, China
| | - Zihao Chu
- School of Computer and Control Engineering, Yantai University, Yantai 264005, China
| | - Hao Chen
- School of Computer and Control Engineering, Yantai University, Yantai 264005, China
| |
Collapse
|
3
|
Katona K, Neamah HA, Korondi P. Obstacle Avoidance and Path Planning Methods for Autonomous Navigation of Mobile Robot. SENSORS (BASEL, SWITZERLAND) 2024; 24:3573. [PMID: 38894362 PMCID: PMC11175283 DOI: 10.3390/s24113573] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/05/2024] [Revised: 05/25/2024] [Accepted: 05/29/2024] [Indexed: 06/21/2024]
Abstract
Path planning creates the shortest path from the source to the destination based on sensory information obtained from the environment. Within path planning, obstacle avoidance is a crucial task in robotics, as the autonomous operation of robots needs to reach their destination without collisions. Obstacle avoidance algorithms play a key role in robotics and autonomous vehicles. These algorithms enable robots to navigate their environment efficiently, minimizing the risk of collisions and safely avoiding obstacles. This article provides an overview of key obstacle avoidance algorithms, including classic techniques such as the Bug algorithm and Dijkstra's algorithm, and newer developments like genetic algorithms and approaches based on neural networks. It analyzes in detail the advantages, limitations, and application areas of these algorithms and highlights current research directions in obstacle avoidance robotics. This article aims to provide comprehensive insight into the current state and prospects of obstacle avoidance algorithms in robotics applications. It also mentions the use of predictive methods and deep learning strategies.
Collapse
|
4
|
Nisar KS, Anjum MW, Raja MAZ, Shoaib M. Recurrent neural network for the dynamics of Zika virus spreading. AIMS Public Health 2024; 11:432-458. [PMID: 39027393 PMCID: PMC11252581 DOI: 10.3934/publichealth.2024022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2024] [Revised: 03/06/2024] [Accepted: 03/13/2024] [Indexed: 07/20/2024] Open
Abstract
Recurrent Neural Networks (RNNs), a type of machine learning technique, have recently drawn a lot of interest in numerous fields, including epidemiology. Implementing public health interventions in the field of epidemiology depends on efficient modeling and outbreak prediction. Because RNNs can capture sequential dependencies in data, they have become highly effective tools in this field. In this paper, the use of RNNs in epidemic modeling is examined, with a focus on the extent to which they can handle the inherent temporal dynamics in the spread of diseases. The mathematical representation of epidemics requires taking time-dependent variables into account, such as the rate at which infections spread and the long-term effects of interventions. The goal of this study is to use an intelligent computing solution based on RNNs to provide numerical performances and interpretations for the SEIR nonlinear system based on the propagation of the Zika virus (SEIRS-PZV) model. The four patient dynamics, namely susceptible patients S(y), exposed patients admitted in a hospital E(y), the fraction of infective individuals I(y), and recovered patients R(y), are represented by the epidemic version of the nonlinear system, or the SEIR model. SEIRS-PZV is represented by ordinary differential equations (ODEs), which are then solved by the Adams method using the Mathematica software to generate a dataset. The dataset was used as an output for the RNN to train the model and examine results such as regressions, correlations, error histograms, etc. For RNN, we used 100% to train the model with 15 hidden layers and a delay of 2 seconds. The input for the RNN is a time series sequence from 0 to 5, with a step size of 0.05. In the end, we compared the approximated solution with the exact solution by plotting them on the same graph and generating the absolute error plot for each of the 4 cases of SEIRS-PZV. Predictions made by the model appeared to be become more accurate when the mean squared error (MSE) decreased. An increased fit to the observed data was suggested by this decrease in the MSE, which suggested that the variance between the model's predicted values and the actual values was dropping. A minimal absolute error almost equal to zero was obtained, which further supports the usefulness of the suggested strategy. A small absolute error shows the degree to which the model's predictions matches the ground truth values, thus indicating the level of accuracy and precision for the model's output.
Collapse
Affiliation(s)
- Kottakkaran Sooppy Nisar
- Department of Mathematics, College of Science and Humanities in Al Kharj, Prince Sattam bin Abdulaziz University, 11942, Saudi Arabia
- Saveetha School of Engineering, SIMATS, Chennai, India
| | | | - Muhammad Asif Zahoor Raja
- Future Technology Research Center, National Yunlin University of Science and Technology, 123 University Road, Section .3, Douliou, Yunlin 64002, Taiwan, R.O.C
| | | |
Collapse
|
5
|
Lu Z, Golomb JD. Human EEG and artificial neural networks reveal disentangled representations of object real-world size in natural images. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2023.08.19.553999. [PMID: 37662197 PMCID: PMC10473678 DOI: 10.1101/2023.08.19.553999] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/05/2023]
Abstract
Remarkably, human brains have the ability to accurately perceive and process the real-world size of objects, despite vast differences in distance and perspective. While previous studies have delved into this phenomenon, distinguishing this ability from other visual perceptions, like depth, has been challenging. Using the THINGS EEG2 dataset with high time-resolution human brain recordings and more ecologically valid naturalistic stimuli, our study uses an innovative approach to disentangle neural representations of object real-world size from retinal size and perceived real-world depth in a way that was not previously possible. Leveraging this state-of-the-art dataset, our EEG representational similarity results reveal a pure representation of object real-world size in human brains. We report a representational timeline of visual object processing: object real-world depth appeared first, then retinal size, and finally, real-world size. Additionally, we input both these naturalistic images and object-only images without natural background into artificial neural networks. Consistent with the human EEG findings, we also successfully disentangled representation of object real-world size from retinal size and real-world depth in all three types of artificial neural networks (visual-only ResNet, visual-language CLIP, and language-only Word2Vec). Moreover, our multi-modal representational comparison framework across human EEG and artificial neural networks reveals real-world size as a stable and higher-level dimension in object space incorporating both visual and semantic information. Our research provides a detailed and clear characterization of the object processing process, which offers further advances and insights into our understanding of object space and the construction of more brain-like visual models.
Collapse
|
6
|
Li W, Li J, Chu C, Cao D, Shi W, Zhang Y, Jiang T. Common Sequential Organization of Face Processing in the Human Brain and Convolutional Neural Networks. Neuroscience 2024; 541:1-13. [PMID: 38266906 DOI: 10.1016/j.neuroscience.2024.01.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 01/11/2024] [Accepted: 01/16/2024] [Indexed: 01/26/2024]
Abstract
Face processing includes two crucial processing levels - face detection and face recognition. However, it remains unclear how human brains organize the two processing levels sequentially. While some studies found that faces are recognized as fast as they are detected, others have reported that faces are detected first, followed by recognition. We discriminated the two processing levels on a fine time scale by combining human intracranial EEG (two females, three males, and three subjects without reported sex information) and representation similarity analysis. Our results demonstrate that the human brain exhibits a "detection-first, recognition-later" pattern during face processing. In addition, we used convolutional neural networks to test the hypothesis that the sequential organization of the two face processing levels in the brain reflects computational optimization. Our findings showed that the networks trained on face recognition also exhibited the "detection-first, recognition-later" pattern. Moreover, this sequential organization mechanism developed gradually during the training of the networks and was observed only for correctly predicted images. These findings collectively support the computational account as to why the brain organizes them in this way.
Collapse
Affiliation(s)
- Wenlu Li
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
| | - Jin Li
- School of Psychology, Capital Normal University, Beijing 100048, China
| | - Congying Chu
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Dan Cao
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Weiyang Shi
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Yu Zhang
- Research Center for Augmented Intelligence, Zhejiang Lab, Hangzhou 311100, China
| | - Tianzi Jiang
- Brainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China; Research Center for Augmented Intelligence, Zhejiang Lab, Hangzhou 311100, China; Xiaoxiang Institute for Brain Health and Yongzhou Central Hospital, Yongzhou 425000, Hunan Province, China.
| |
Collapse
|
7
|
Avcu E, Gow D. Exploring Abstract Pattern Representation in The Brain and Non-symbolic Neural Networks. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.11.27.568877. [PMID: 38076846 PMCID: PMC10705297 DOI: 10.1101/2023.11.27.568877] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/24/2023]
Abstract
Human cognitive and linguistic generativity depends on the ability to identify abstract relationships between perceptually dissimilar items. Marcus et al. (1999) found that human infants can rapidly discover and generalize patterns of syllable repetition (reduplication) that depend on the abstract property of identity, but simple recurrent neural networks (SRNs) could not. They interpreted these results as evidence that purely associative neural network models provide an inadequate framework for characterizing the fundamental generativity of human cognition. Here, we present a series of deep long short-term memory (LSTM) models that identify abstract syllable repetition patterns and words based on training with cochleagrams that represent auditory stimuli. We demonstrate that models trained to identify individual syllable trigram words and models trained to identify reduplication patterns discover representations that support classification of abstract repetition patterns. Simulations examined the effects of training categories (words vs. patterns) and pretraining to identify syllables, on the development of hidden node representations that support repetition pattern discrimination. Representational similarity analyses (RSA) comparing patterns of regional brain activity based on MRI-constrained MEG/EEG data to patterns of hidden node activation elicited by the same stimuli showed a significant correlation between brain activity localized in primarily posterior temporal regions and representations discovered by the models. These results suggest that associative mechanisms operating over discoverable representations that capture abstract stimulus properties account for a critical example of human cognitive generativity.
Collapse
Affiliation(s)
- Enes Avcu
- Department of Neurology, Massachusetts General Hospital, Cambridge, MA 02170
| | - David Gow
- Department of Neurology, Massachusetts General Hospital, Cambridge, MA 02170
| |
Collapse
|
8
|
Tanaka R, Zhou B, Agrochao M, Badwan BA, Au B, Matos NCB, Clark DA. Neural mechanisms to incorporate visual counterevidence in self-movement estimation. Curr Biol 2023; 33:4960-4979.e7. [PMID: 37918398 PMCID: PMC10848174 DOI: 10.1016/j.cub.2023.10.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2023] [Revised: 10/07/2023] [Accepted: 10/09/2023] [Indexed: 11/04/2023]
Abstract
In selecting appropriate behaviors, animals should weigh sensory evidence both for and against specific beliefs about the world. For instance, animals measure optic flow to estimate and control their own rotation. However, existing models of flow detection can be spuriously triggered by visual motion created by objects moving in the world. Here, we show that stationary patterns on the retina, which constitute evidence against observer rotation, suppress inappropriate stabilizing rotational behavior in the fruit fly Drosophila. In silico experiments show that artificial neural networks (ANNs) that are optimized to distinguish observer movement from external object motion similarly detect stationarity and incorporate negative evidence. Employing neural measurements and genetic manipulations, we identified components of the circuitry for stationary pattern detection, which runs parallel to the fly's local motion and optic-flow detectors. Our results show how the fly brain incorporates negative evidence to improve heading stability, exemplifying how a compact brain exploits geometrical constraints of the visual world.
Collapse
Affiliation(s)
- Ryosuke Tanaka
- Interdepartmental Neuroscience Program, Yale University, New Haven, CT 06511, USA
| | - Baohua Zhou
- Department of Molecular Cellular and Developmental Biology, Yale University, New Haven, CT 06511, USA; Department of Statistics and Data Science, Yale University, New Haven, CT 06511, USA
| | - Margarida Agrochao
- Department of Molecular Cellular and Developmental Biology, Yale University, New Haven, CT 06511, USA
| | - Bara A Badwan
- School of Engineering and Applied Science, Yale University, New Haven, CT 06511, USA
| | - Braedyn Au
- Department of Physics, Yale University, New Haven, CT 06511, USA
| | - Natalia C B Matos
- Interdepartmental Neuroscience Program, Yale University, New Haven, CT 06511, USA
| | - Damon A Clark
- Department of Molecular Cellular and Developmental Biology, Yale University, New Haven, CT 06511, USA; Department of Physics, Yale University, New Haven, CT 06511, USA; Department of Neuroscience, Yale University, New Haven, CT 06511, USA; Wu Tsai Institute, Yale University, New Haven, CT 06511, USA; Quantitative Biology Institute, Yale University, New Haven, CT 06511, USA.
| |
Collapse
|
9
|
Vafaii H, Yates JL, Butts DA. Hierarchical VAEs provide a normative account of motion processing in the primate brain. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.09.27.559646. [PMID: 37808629 PMCID: PMC10557690 DOI: 10.1101/2023.09.27.559646] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/10/2023]
Abstract
The relationship between perception and inference, as postulated by Helmholtz in the 19th century, is paralleled in modern machine learning by generative models like Variational Autoencoders (VAEs) and their hierarchical variants. Here, we evaluate the role of hierarchical inference and its alignment with brain function in the domain of motion perception. We first introduce a novel synthetic data framework, Retinal Optic Flow Learning (ROFL), which enables control over motion statistics and their causes. We then present a new hierarchical VAE and test it against alternative models on two downstream tasks: (i) predicting ground truth causes of retinal optic flow (e.g., self-motion); and (ii) predicting the responses of neurons in the motion processing pathway of primates. We manipulate the model architectures (hierarchical versus non-hierarchical), loss functions, and the causal structure of the motion stimuli. We find that hierarchical latent structure in the model leads to several improvements. First, it improves the linear decodability of ground truth factors and does so in a sparse and disentangled manner. Second, our hierarchical VAE outperforms previous state-of-the-art models in predicting neuronal responses and exhibits sparse latent-to-neuron relationships. These results depend on the causal structure of the world, indicating that alignment between brains and artificial neural networks depends not only on architecture but also on matching ecologically relevant stimulus statistics. Taken together, our results suggest that hierarchical Bayesian inference underlines the brain's understanding of the world, and hierarchical VAEs can effectively model this understanding.
Collapse
|
10
|
van Dyck LE, Gruber WR. Modeling Biological Face Recognition with Deep Convolutional Neural Networks. J Cogn Neurosci 2023; 35:1521-1537. [PMID: 37584587 DOI: 10.1162/jocn_a_02040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/17/2023]
Abstract
Deep convolutional neural networks (DCNNs) have become the state-of-the-art computational models of biological object recognition. Their remarkable success has helped vision science break new ground, and recent efforts have started to transfer this achievement to research on biological face recognition. In this regard, face detection can be investigated by comparing face-selective biological neurons and brain areas to artificial neurons and model layers. Similarly, face identification can be examined by comparing in vivo and in silico multidimensional "face spaces." In this review, we summarize the first studies that use DCNNs to model biological face recognition. On the basis of a broad spectrum of behavioral and computational evidence, we conclude that DCNNs are useful models that closely resemble the general hierarchical organization of face recognition in the ventral visual pathway and the core face network. In two exemplary spotlights, we emphasize the unique scientific contributions of these models. First, studies on face detection in DCNNs indicate that elementary face selectivity emerges automatically through feedforward processing even in the absence of visual experience. Second, studies on face identification in DCNNs suggest that identity-specific experience and generative mechanisms facilitate this particular challenge. Taken together, as this novel modeling approach enables close control of predisposition (i.e., architecture) and experience (i.e., training data), it may be suited to inform long-standing debates on the substrates of biological face recognition.
Collapse
|
11
|
Palaniyappan L, Benrimoh D, Voppel A, Rocca R. Studying Psychosis Using Natural Language Generation: A Review of Emerging Opportunities. BIOLOGICAL PSYCHIATRY. COGNITIVE NEUROSCIENCE AND NEUROIMAGING 2023; 8:994-1004. [PMID: 38441079 DOI: 10.1016/j.bpsc.2023.04.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Revised: 04/16/2023] [Accepted: 04/19/2023] [Indexed: 03/07/2024]
Abstract
Disrupted language in psychotic disorders, such as schizophrenia, can manifest as false contents and formal deviations, often described as thought disorder. These features play a critical role in the social dysfunction associated with psychosis, but we continue to lack insights regarding how and why these symptoms develop. Natural language generation (NLG) is a field of computer science that focuses on generating human-like language for various applications. The theory that psychosis is related to the evolution of language in humans suggests that NLG systems that are sufficiently evolved to generate human-like language may also exhibit psychosis-like features. In this conceptual review, we propose using NLG systems that are at various stages of development as in silico tools to study linguistic features of psychosis. We argue that a program of in silico experimental research on the network architecture, function, learning rules, and training of NLG systems can help us understand better why thought disorder occurs in patients. This will allow us to gain a better understanding of the relationship between language and psychosis and potentially pave the way for new therapeutic approaches to address this vexing challenge.
Collapse
Affiliation(s)
- Lena Palaniyappan
- Douglas Mental Health University Institute, Department of Psychiatry, McGill University, Montreal, Quebec, Canada; Robarts Research Institute, Western University, London, Ontario, Canada; Department of Medical Biophysics, Western University, London, Ontario, Canada.
| | - David Benrimoh
- Douglas Mental Health University Institute, Department of Psychiatry, McGill University, Montreal, Quebec, Canada; Department of Psychiatry, Stanford University, Palo Alto, California
| | - Alban Voppel
- Douglas Mental Health University Institute, Department of Psychiatry, McGill University, Montreal, Quebec, Canada; Department of Psychiatry, University of Groningen, Groningen, the Netherlands
| | - Roberta Rocca
- Interacting Minds Centre, Department of Culture, Cognition and Computation, Aarhus University, Aarhus, Denmark
| |
Collapse
|
12
|
Bhoj S, Gaur GK, Tarafdar A. An intelligent model for predicting the dressed weight of pigs using morphometric measurements. JOURNAL OF FOOD SCIENCE AND TECHNOLOGY 2023; 60:1841-1845. [PMID: 37187982 PMCID: PMC10169999 DOI: 10.1007/s13197-023-05704-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Revised: 02/13/2023] [Accepted: 02/21/2023] [Indexed: 03/06/2023]
Abstract
Determining the slaughter weight of pigs is crucial to the profitability of swine production farms. Unfortunately, in developing countries, the basic infrastructure for weight measurement may not always be available, affecting farmers' income. This study presents a machine learning-based approach to determine the dressed weight of pigs using four morphometric dimensions: paunch girth (PG), heart girth (HG), body length and wither height, which can be measured in situ. Different neural network model structures were constructed taking LM, GDX and BR training algorithms, tansigmoid/logsigmoid hidden layer transfer functions and 5-30 hidden layer neurons (HLNs). Results showed that LM training algorithm with logsigmoidal transfer function and 20 HLNs resulted in 99.8% accuracy in determining the pig dressed weight. Further, the number of morphometric parameters as inputs was gradually reduced and it was found that 99% accuracy can still be achieved using just PG and HG, thereby reducing the measurement time.
Collapse
Affiliation(s)
- Suvarna Bhoj
- Livestock Production and Management (LPM) Section, ICAR-Indian Veterinary Research Institute, Izzatnagar, Bareilly, Uttar Pradesh 243 122 India
| | - Gyanendra Kumar Gaur
- Livestock Production and Management (LPM) Section, ICAR-Indian Veterinary Research Institute, Izzatnagar, Bareilly, Uttar Pradesh 243 122 India
| | - Ayon Tarafdar
- Livestock Production and Management (LPM) Section, ICAR-Indian Veterinary Research Institute, Izzatnagar, Bareilly, Uttar Pradesh 243 122 India
| |
Collapse
|
13
|
Doerig A, Sommers RP, Seeliger K, Richards B, Ismael J, Lindsay GW, Kording KP, Konkle T, van Gerven MAJ, Kriegeskorte N, Kietzmann TC. The neuroconnectionist research programme. Nat Rev Neurosci 2023:10.1038/s41583-023-00705-w. [PMID: 37253949 DOI: 10.1038/s41583-023-00705-w] [Citation(s) in RCA: 14] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/21/2023] [Indexed: 06/01/2023]
Abstract
Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have been not only lauded as the current best models of information processing in the brain but also criticized for failing to account for basic cognitive functions. In this Perspective article, we propose that arguing about the successes and failures of a restricted set of current ANNs is the wrong approach to assess the promise of neuroconnectionism for brain science. Instead, we take inspiration from the philosophy of science, and in particular from Lakatos, who showed that the core of a scientific research programme is often not directly falsifiable but should be assessed by its capacity to generate novel insights. Following this view, we present neuroconnectionism as a general research programme centred around ANNs as a computational language for expressing falsifiable theories about brain computation. We describe the core of the programme, the underlying computational framework and its tools for testing specific neuroscientific hypotheses and deriving novel understanding. Taking a longitudinal view, we review past and present neuroconnectionist projects and their responses to challenges and argue that the research programme is highly progressive, generating new and otherwise unreachable insights into the workings of the brain.
Collapse
Affiliation(s)
- Adrien Doerig
- Institute of Cognitive Science, University of Osnabrück, Osnabrück, Germany.
- Donders Institute for Brain, Cognition and Behaviour, Nijmegen, The Netherlands.
| | - Rowan P Sommers
- Department of Neurobiology of Language, Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands
| | - Katja Seeliger
- Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany
| | - Blake Richards
- Department of Neurology and Neurosurgery, McGill University, Montréal, QC, Canada
- School of Computer Science, McGill University, Montréal, QC, Canada
- Mila, Montréal, QC, Canada
- Montréal Neurological Institute, Montréal, QC, Canada
- Learning in Machines and Brains Program, CIFAR, Toronto, ON, Canada
| | | | | | - Konrad P Kording
- Learning in Machines and Brains Program, CIFAR, Toronto, ON, Canada
- Bioengineering, Neuroscience, University of Pennsylvania, Pennsylvania, PA, USA
| | | | | | | | - Tim C Kietzmann
- Institute of Cognitive Science, University of Osnabrück, Osnabrück, Germany
| |
Collapse
|
14
|
Yovel G, Grosbard I, Abudarham N. Deep learning models challenge the prevailing assumption that face-like effects for objects of expertise support domain-general mechanisms. Proc Biol Sci 2023; 290:20230093. [PMID: 37161322 PMCID: PMC10170201 DOI: 10.1098/rspb.2023.0093] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2023] [Accepted: 04/04/2023] [Indexed: 05/11/2023] Open
Abstract
The question of whether task performance is best achieved by domain-specific, or domain-general processing mechanisms is fundemental for both artificial and biological systems. This question has generated a fierce debate in the study of expert object recognition. Because humans are experts in face recognition, face-like neural and cognitive effects for objects of expertise were considered support for domain-general mechanisms. However, effects of domain, experience and level of categorization, are confounded in human studies, which may lead to erroneous inferences. To overcome these limitations, we trained deep learning algorithms on different domains (objects, faces, birds) and levels of categorization (basic, sub-ordinate, individual), matched for amount of experience. Like humans, the models generated a larger inversion effect for faces than for objects. Importantly, a face-like inversion effect was found for individual-based categorization of non-faces (birds) but only in a network specialized for that domain. Thus, contrary to prevalent assumptions, face-like effects for objects of expertise do not support domain-general mechanisms but may originate from domain-specific mechanisms. More generally, we show how deep learning algorithms can be used to dissociate factors that are inherently confounded in the natural environment of biological organisms to test hypotheses about their isolated contributions to cognition and behaviour.
Collapse
Affiliation(s)
- Galit Yovel
- School of Psychological Sciences, Tel Aviv University, Tel Aviv 69987, Israel
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv 69987, Israel
| | - Idan Grosbard
- School of Psychological Sciences, Tel Aviv University, Tel Aviv 69987, Israel
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv 69987, Israel
| | - Naphtali Abudarham
- School of Psychological Sciences, Tel Aviv University, Tel Aviv 69987, Israel
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv 69987, Israel
| |
Collapse
|
15
|
Avcu E, Hwang M, Brown KS, Gow DW. A tale of two lexica: Investigating computational pressures on word representation with neural networks. Front Artif Intell 2023; 6:1062230. [PMID: 37051161 PMCID: PMC10083378 DOI: 10.3389/frai.2023.1062230] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Accepted: 03/10/2023] [Indexed: 03/28/2023] Open
Abstract
Introduction The notion of a single localized store of word representations has become increasingly less plausible as evidence has accumulated for the widely distributed neural representation of wordform grounded in motor, perceptual, and conceptual processes. Here, we attempt to combine machine learning methods and neurobiological frameworks to propose a computational model of brain systems potentially responsible for wordform representation. We tested the hypothesis that the functional specialization of word representation in the brain is driven partly by computational optimization. This hypothesis directly addresses the unique problem of mapping sound and articulation vs. mapping sound and meaning. Results We found that artificial neural networks trained on the mapping between sound and articulation performed poorly in recognizing the mapping between sound and meaning and vice versa. Moreover, a network trained on both tasks simultaneously could not discover the features required for efficient mapping between sound and higher-level cognitive states compared to the other two models. Furthermore, these networks developed internal representations reflecting specialized task-optimized functions without explicit training. Discussion Together, these findings demonstrate that different task-directed representations lead to more focused responses and better performance of a machine or algorithm and, hypothetically, the brain. Thus, we imply that the functional specialization of word representation mirrors a computational optimization strategy given the nature of the tasks that the human brain faces.
Collapse
Affiliation(s)
- Enes Avcu
- Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | | | - Kevin Scott Brown
- Department of Pharmaceutical Sciences and School of Chemical, Biological, and Environmental Engineering, Oregon State University, Corvallis, OR, United States
| | - David W. Gow
- Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
- Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital, Charlestown, MA, United States
- Department of Psychology, Salem State University, Salem, MA, United States
- Harvard-MIT Division of Health Sciences and Technology, Boston, MA, United States
| |
Collapse
|
16
|
Kanwisher N, Gupta P, Dobs K. CNNs reveal the computational implausibility of the expertise hypothesis. iScience 2023; 26:105976. [PMID: 36794151 PMCID: PMC9923184 DOI: 10.1016/j.isci.2023.105976] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Revised: 11/07/2022] [Accepted: 01/11/2023] [Indexed: 01/15/2023] Open
Abstract
Face perception has long served as a classic example of domain specificity of mind and brain. But an alternative "expertise" hypothesis holds that putatively face-specific mechanisms are actually domain-general, and can be recruited for the perception of other objects of expertise (e.g., cars for car experts). Here, we demonstrate the computational implausibility of this hypothesis: Neural network models optimized for generic object categorization provide a better foundation for expert fine-grained discrimination than do models optimized for face recognition.
Collapse
Affiliation(s)
- Nancy Kanwisher
- Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, USA,McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | - Pranjul Gupta
- Department of Psychology, Justus-Liebig University Giessen, 35394 Giessen, Germany
| | - Katharina Dobs
- Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, USA,McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA,Department of Psychology, Justus-Liebig University Giessen, 35394 Giessen, Germany,Center for Mind, Brain and Behavior (CMBB), University of Marburg and Justus-Liebig University, 35032 Marburg, Germany,Corresponding author
| |
Collapse
|