1
|
Wang C, Ying Z, Pan Z. Machine unlearning in brain-inspired neural network paradigms. Front Neurorobot 2024; 18:1361577. [PMID: 38835363 PMCID: PMC11148458 DOI: 10.3389/fnbot.2024.1361577] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Accepted: 03/11/2024] [Indexed: 06/06/2024] Open
Abstract
Machine unlearning, which is crucial for data privacy and regulatory compliance, involves the selective removal of specific information from a machine learning model. This study focuses on implementing machine unlearning in Spiking Neuron Models (SNMs) that closely mimic biological neural network behaviors, aiming to enhance both flexibility and ethical compliance of AI models. We introduce a novel hybrid approach for machine unlearning in SNMs, which combines selective synaptic retraining, synaptic pruning, and adaptive neuron thresholding. This methodology is designed to effectively eliminate targeted information while preserving the overall integrity and performance of the neural network. Extensive experiments were conducted on various computer vision datasets to assess the impact of machine unlearning on critical performance metrics such as accuracy, precision, recall, and ROC AUC. Our findings indicate that the hybrid approach not only maintains but in some cases enhances the neural network's performance post-unlearning. The results confirm the practicality and efficiency of our approach, underscoring its applicability in real-world AI systems.
Collapse
Affiliation(s)
- Chaoyi Wang
- Faculty of Data Science, City University of Macau, Macao, Macao SAR, China
| | - Zuobin Ying
- Faculty of Data Science, City University of Macau, Macao, Macao SAR, China
| | - Zijie Pan
- Faculty of Data Science, City University of Macau, Macao, Macao SAR, China
| |
Collapse
|
2
|
Cotteret M, Greatorex H, Ziegler M, Chicca E. Vector Symbolic Finite State Machines in Attractor Neural Networks. Neural Comput 2024; 36:549-595. [PMID: 38457766 DOI: 10.1162/neco_a_01638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 10/19/2023] [Indexed: 03/10/2024]
Abstract
Hopfield attractor networks are robust distributed models of human memory, but they lack a general mechanism for effecting state-dependent attractor transitions in response to input. We propose construction rules such that an attractor network may implement an arbitrary finite state machine (FSM), where states and stimuli are represented by high-dimensional random vectors and all state transitions are enacted by the attractor network's dynamics. Numerical simulations show the capacity of the model, in terms of the maximum size of implementable FSM, to be linear in the size of the attractor network for dense bipolar state vectors and approximately quadratic for sparse binary state vectors. We show that the model is robust to imprecise and noisy weights, and so a prime candidate for implementation with high-density but unreliable devices. By endowing attractor networks with the ability to emulate arbitrary FSMs, we propose a plausible path by which FSMs could exist as a distributed computational primitive in biological neural networks.
Collapse
Affiliation(s)
- Madison Cotteret
- Micro- and Nanoelectronic Systems, Institute of Micro- and Nanotechnologies (IMN) MacroNano, Technische Universität Ilmenau, 98693 Ilmenau, Germany
- Bio-Inspired Circuits and Systems Lab, Zernike Institute for Advanced Materials, and Groningen Cognitive Systems and Materials Center, University of Groningen, 9747 AG Groningen, Netherlands
| | - Hugh Greatorex
- Bio-Inspired Circuits and Systems Lab, Zernike Institute for Advanced Materials, and Groningen Cognitive Systems and Materials Center, University of Groningen, 9747 AG Groningen, Netherlands
| | - Martin Ziegler
- Micro- and Nanoelectronic Systems, Institute of Micro- and Nanotechnologies (IMN) MacroNano, Technische Universität Ilmenau, 98693 Ilmenau, Germany
| | - Elisabetta Chicca
- Bio-Inspired Circuits and Systems Lab, Zernike Institute for Advanced Materials, and Groningen Cognitive Systems and Materials Center, University of Groningen, 9747 AG Groningen, Netherlands
| |
Collapse
|
3
|
Maslennikov O, Perc M, Nekorkin V. Topological features of spike trains in recurrent spiking neural networks that are trained to generate spatiotemporal patterns. Front Comput Neurosci 2024; 18:1363514. [PMID: 38463243 PMCID: PMC10920356 DOI: 10.3389/fncom.2024.1363514] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2023] [Accepted: 02/06/2024] [Indexed: 03/12/2024] Open
Abstract
In this study, we focus on training recurrent spiking neural networks to generate spatiotemporal patterns in the form of closed two-dimensional trajectories. Spike trains in the trained networks are examined in terms of their dissimilarity using the Victor-Purpura distance. We apply algebraic topology methods to the matrices obtained by rank-ordering the entries of the distance matrices, specifically calculating the persistence barcodes and Betti curves. By comparing the features of different types of output patterns, we uncover the complex relations between low-dimensional target signals and the underlying multidimensional spike trains.
Collapse
Affiliation(s)
- Oleg Maslennikov
- Federal Research Center A.V. Gaponov-Grekhov Institute of Applied Physics of the Russian Academy of Sciences, Nizhny Novgorod, Russia
| | - Matjaž Perc
- Faculty of Natural Sciences and Mathematics, University of Maribor, Maribor, Slovenia
- Department of Medical Research, China Medical University Hospital, China Medical University, Taichung City, Taiwan
- Complexity Science Hub Vienna, Vienna, Austria
- Department of Physics, Kyung Hee University, Seoul, Republic of Korea
| | - Vladimir Nekorkin
- Federal Research Center A.V. Gaponov-Grekhov Institute of Applied Physics of the Russian Academy of Sciences, Nizhny Novgorod, Russia
| |
Collapse
|
4
|
Sakemi Y, Yamamoto K, Hosomi T, Aihara K. Sparse-firing regularization methods for spiking neural networks with time-to-first-spike coding. Sci Rep 2023; 13:22897. [PMID: 38129555 PMCID: PMC10739753 DOI: 10.1038/s41598-023-50201-5] [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: 08/09/2023] [Accepted: 12/16/2023] [Indexed: 12/23/2023] Open
Abstract
The training of multilayer spiking neural networks (SNNs) using the error backpropagation algorithm has made significant progress in recent years. Among the various training schemes, the error backpropagation method that directly uses the firing time of neurons has attracted considerable attention because it can realize ideal temporal coding. This method uses time-to-first-spike (TTFS) coding, in which each neuron fires at most once, and this restriction on the number of firings enables information to be processed at a very low firing frequency. This low firing frequency increases the energy efficiency of information processing in SNNs. However, only an upper limit has been provided for TTFS-coded SNNs, and the information-processing capability of SNNs at lower firing frequencies has not been fully investigated. In this paper, we propose two spike-timing-based sparse-firing (SSR) regularization methods to further reduce the firing frequency of TTFS-coded SNNs. Both methods are characterized by the fact that they only require information about the firing timing and associated weights. The effects of these regularization methods were investigated on the MNIST, Fashion-MNIST, and CIFAR-10 datasets using multilayer perceptron networks and convolutional neural network structures.
Collapse
Affiliation(s)
- Yusuke Sakemi
- Research Center for Mathematical Engineering, Chiba Institute of Technology, Narashino, Japan.
- International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo, Tokyo, Japan.
| | | | | | - Kazuyuki Aihara
- Research Center for Mathematical Engineering, Chiba Institute of Technology, Narashino, Japan
- International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo, Tokyo, Japan
| |
Collapse
|
5
|
Yang G, Lee W, Seo Y, Lee C, Seok W, Park J, Sim D, Park C. Unsupervised Spiking Neural Network with Dynamic Learning of Inhibitory Neurons. SENSORS (BASEL, SWITZERLAND) 2023; 23:7232. [PMID: 37631767 PMCID: PMC10459513 DOI: 10.3390/s23167232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 07/23/2023] [Accepted: 08/15/2023] [Indexed: 08/27/2023]
Abstract
A spiking neural network (SNN) is a type of artificial neural network that operates based on discrete spikes to process timing information, similar to the manner in which the human brain processes real-world problems. In this paper, we propose a new spiking neural network (SNN) based on conventional, biologically plausible paradigms, such as the leaky integrate-and-fire model, spike timing-dependent plasticity, and the adaptive spiking threshold, by suggesting new biological models; that is, dynamic inhibition weight change, a synaptic wiring method, and Bayesian inference. The proposed network is designed for image recognition tasks, which are frequently used to evaluate the performance of conventional deep neural networks. To manifest the bio-realistic neural architecture, the learning is unsupervised, and the inhibition weight is dynamically changed; this, in turn, affects the synaptic wiring method based on Hebbian learning and the neuronal population. In the inference phase, Bayesian inference successfully classifies the input digits by counting the spikes from the responding neurons. The experimental results demonstrate that the proposed biological model ensures a performance improvement compared with other biologically plausible SNN models.
Collapse
Affiliation(s)
- Geunbo Yang
- Department of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (G.Y.); (Y.S.); (C.L.)
| | - Wongyu Lee
- Department of Intelligent Information and Embedded Software Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (W.L.); (W.S.)
| | - Youjung Seo
- Department of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (G.Y.); (Y.S.); (C.L.)
| | - Choongseop Lee
- Department of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (G.Y.); (Y.S.); (C.L.)
| | - Woojoon Seok
- Department of Intelligent Information and Embedded Software Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (W.L.); (W.S.)
| | - Jongkil Park
- Center for Neuromorphic Engineering, Korea Institute of Science and Technology (KIST), Seoul 02792, Republic of Korea;
| | - Donggyu Sim
- Department of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (G.Y.); (Y.S.); (C.L.)
| | - Cheolsoo Park
- Department of Computer Engineering, Kwangwoon University, Seoul 01897, Republic of Korea; (G.Y.); (Y.S.); (C.L.)
| |
Collapse
|
6
|
Saemaldahr R, Ilyas M. Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning. SENSORS (BASEL, SWITZERLAND) 2023; 23:6578. [PMID: 37514873 PMCID: PMC10385318 DOI: 10.3390/s23146578] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 07/15/2023] [Accepted: 07/17/2023] [Indexed: 07/30/2023]
Abstract
Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.
Collapse
Affiliation(s)
- Raghdah Saemaldahr
- Department of Computer Science, Taibah University, Medina 42353, Saudi Arabia
- Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA
| | - Mohammad Ilyas
- Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA
| |
Collapse
|
7
|
Wu X, Feng Y, Lou S, Zheng H, Hu B, Hong Z, Tan J. Improving NeuCube Spiking Neural Network for EEG-based Pattern Recognition Using Transfer Learning. Neurocomputing 2023. [DOI: 10.1016/j.neucom.2023.01.087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
|
8
|
Akl M, Ergene D, Walter F, Knoll A. Toward robust and scalable deep spiking reinforcement learning. Front Neurorobot 2023; 16:1075647. [PMID: 36742191 PMCID: PMC9894879 DOI: 10.3389/fnbot.2022.1075647] [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: 10/20/2022] [Accepted: 12/23/2022] [Indexed: 01/21/2023] Open
Abstract
Deep reinforcement learning (DRL) combines reinforcement learning algorithms with deep neural networks (DNNs). Spiking neural networks (SNNs) have been shown to be a biologically plausible and energy efficient alternative to DNNs. Since the introduction of surrogate gradient approaches that allowed to overcome the discontinuity in the spike function, SNNs can now be trained with the backpropagation through time (BPTT) algorithm. While largely explored on supervised learning problems, little work has been done on investigating the use of SNNs as function approximators in DRL. Here we show how SNNs can be applied to different DRL algorithms like Deep Q-Network (DQN) and Twin-Delayed Deep Deteministic Policy Gradient (TD3) for discrete and continuous action space environments, respectively. We found that SNNs are sensitive to the additional hyperparameters introduced by spiking neuron models like current and voltage decay factors, firing thresholds, and that extensive hyperparameter tuning is inevitable. However, we show that increasing the simulation time of SNNs, as well as applying a two-neuron encoding to the input observations helps reduce the sensitivity to the membrane parameters. Furthermore, we show that randomizing the membrane parameters, instead of selecting uniform values for all neurons, has stabilizing effects on the training. We conclude that SNNs can be utilized for learning complex continuous control problems with state-of-the-art DRL algorithms. While the training complexity increases, the resulting SNNs can be directly executed on neuromorphic processors and potentially benefit from their high energy efficiency.
Collapse
|
9
|
Wang K, Hao X, Wang J, Deng B. Comparison and Selection of Spike Encoding Algorithms for SNN on FPGA. IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS 2023; PP:129-141. [PMID: 37021893 DOI: 10.1109/tbcas.2023.3238165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
The information in Spiking Neural Networks (SNNs) is carried by discrete spikes. Therefore, the conversion between the spiking signals and real-value signals has an important impact on the encoding efficiency and performance of SNNs, which is usually completed by spike encoding algorithms. In order to select suitable spike encoding algorithms for different SNNs, this work evaluates four commonly used spike encoding algorithms. The evaluation is based on the FPGA implementation results of the algorithms, including calculation speed, resource consumption, accuracy, and anti-noiseability, so as to better adapt to the neuromorphic implementation of SNN. Two real-world applicaitons are also used to verify the evaluation results. By analyzing and comparing the evaluation results, this work summarizes the characteristics and application range of different algorithms. In general, the sliding window algorithm has relatively low accuracy and is suitable for observing signal trends. Pulsewidth modulated-Based algorithm and step-forward algorithm are suitable for accurate reconstruction of various signals except for square wave signals, while Ben's Spiker algorithm can remedy this. Finally, a scoring method that can be used for spiking coding algorithm selection is proposed, which can help to improve the encoding efficiency of neuromorphic SNNs.
Collapse
|
10
|
Forno E, Fra V, Pignari R, Macii E, Urgese G. Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task. Front Neurosci 2022; 16:999029. [PMID: 36620463 PMCID: PMC9811205 DOI: 10.3389/fnins.2022.999029] [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: 07/20/2022] [Accepted: 11/30/2022] [Indexed: 12/24/2022] Open
Abstract
Spiking Neural Networks (SNNs), known for their potential to enable low energy consumption and computational cost, can bring significant advantages to the realm of embedded machine learning for edge applications. However, input coming from standard digital sensors must be encoded into spike trains before it can be elaborated with neuromorphic computing technologies. We present here a detailed comparison of available spike encoding techniques for the translation of time-varying signals into the event-based signal domain, tested on two different datasets both acquired through commercially available digital devices: the Free Spoken Digit dataset (FSD), consisting of 8-kHz audio files, and the WISDM dataset, composed of 20-Hz recordings of human activity through mobile and wearable inertial sensors. We propose a complete pipeline to benchmark these encoding techniques by performing time-dependent signal classification through a Spiking Convolutional Neural Network (sCNN), including a signal preprocessing step consisting of a bank of filters inspired by the human cochlea, feature extraction by production of a sonogram, transfer learning via an equivalent ANN, and model compression schemes aimed at resource optimization. The resulting performance comparison and analysis provides a powerful practical tool, empowering developers to select the most suitable coding method based on the type of data and the desired processing algorithms, and further expands the applicability of neuromorphic computational paradigms to embedded sensor systems widely employed in the IoT and industrial domains.
Collapse
|
11
|
George AM, Dey S, Banerjee D, Mukherjee A, Suri M. Online Time-Series Forecasting using Spiking Reservoir. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.10.067] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
12
|
Wu T, Neri F, Pan L. On the tuning of the computation capability of spiking neural membrane systems with communication on request. Int J Neural Syst 2022; 32:2250037. [DOI: 10.1142/s012906572250037x] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
13
|
Plessas A, Espinosa-Ramos JI, Parry D, Cowie S, Landon J. Machine learning with a snapshot of data: Spiking neural network 'predicts' reinforcement histories of pigeons' choice behavior. J Exp Anal Behav 2022; 117:301-319. [PMID: 35445745 PMCID: PMC9320819 DOI: 10.1002/jeab.759] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2022] [Revised: 03/25/2022] [Accepted: 03/29/2022] [Indexed: 11/20/2022]
Abstract
An accumulated body of choice research has demonstrated that choice behavior can be understood within the context of its history of reinforcement by measuring response patterns. Traditionally, work on predicting choice behaviors has been based on the relationship between the history of reinforcement—the reinforcer arrangement used in training conditions—and choice behavior. We suggest an alternative method that treats the reinforcement history as unknown and focuses only on operant choices to accurately predict (more precisely, retrodict) reinforcement histories. We trained machine learning models known as artificial spiking neural networks (SNNs) on previously published pigeon datasets to detect patterns in choices with specific reinforcement histories—seven arranged concurrent variable‐interval schedules in effect for nine reinforcers. Notably, SNN extracted information from a small ‘window’ of observational data to predict reinforcer arrangements. The models' generalization ability was then tested with new choices of the same pigeons to predict the type of schedule used in training. We examined whether the amount of the data provided affected the prediction accuracy and our results demonstrated that choices made by the pigeons immediately after the delivery of reinforcers provided sufficient information for the model to determine the reinforcement history. These results support the idea that SNNs can process small sets of behavioral data for pattern detection, when the reinforcement history is unknown. This novel approach can influence our decisions to determine appropriate interventions; it can be a valuable addition to our toolbox, for both therapy design and research.
Collapse
Affiliation(s)
| | | | - Dave Parry
- Auckland University of Technology, New Zealand
| | | | | |
Collapse
|
14
|
Time Series Classification Based on Image Transformation Using Feature Fusion Strategy. Neural Process Lett 2022. [DOI: 10.1007/s11063-022-10783-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|