A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots

Score mismatching for generative modeling

We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress all the time steps with the gradient backpropagated from the score network. In order to produce meaningful gradients for the generator, the score network is trained to simultaneously match the real data distribution and mismatch the fake data distribution. This model has the following advantages: (1) For sampling, it generates a fake image with only one step forward. (2) For training, it only needs 10 diffusion steps. (3) Compared with consistency model, it is free of the ill-posed problem caused by consistency loss. On the popular CIFAR-10 dataset, our model outperforms Consistency Model and Denoising Score Matching, which demonstrates the potential of the framework. We further provide more examples on the MINIST and LSUN datasets. The code is available on GitHub.

Applying Generative Artificial Intelligence to cognitive models of decision making

Introduction

Generative Artificial Intelligence has made significant impacts in many fields, including computational cognitive modeling of decision making, although these applications have not yet been theoretically related to each other. This work introduces a categorization of applications of Generative Artificial Intelligence to cognitive models of decision making.

Methods

This categorization is used to compare the existing literature and to provide insight into the design of an ablation study to evaluate our proposed model in three experimental paradigms. These experiments used for model comparison involve modeling human learning and decision making based on both visual information and natural language, in tasks that vary in realism and complexity. This comparison of applications takes as its basis Instance-Based Learning Theory, a theory of experiential decision making from which many models have emerged and been applied to a variety of domains and applications.

Results

The best performing model from the ablation we performed used a generative model to both create memory representations as well as predict participant actions. The results of this comparison demonstrates the importance of generative models in both forming memories and predicting actions in decision-modeling research.

Discussion

In this work, we present a model that integrates generative and cognitive models, using a variety of stimuli, applications, and training methods. These results can provide guidelines for cognitive modelers and decision making researchers interested in integrating Generative AI into their methods.

Factors affecting the adoption of metaverse in healthcare: The moderating role of digital division, and meta-culture

This research aims to find out the factors affecting the adoption of Metaverse in healthcare. This study explores the effect of perceived ease of use, perceived usefulness, and trust on adopting Metaverse in healthcare by keeping digital division and metaculture as moderating variables. The philosophical foundation is rooted in the positivism paradigm, the methodology is quantitative, and the approach used is deductive. Data was collected in Pakistan and China through judgmental sampling from 384 respondents. Partial Least Square Structural Equation Modelling (PLS-SEM) was used to analyze the collected data. The findings validate the relationship between perceived ease of use and the adoption of metaverse with β-value 0.236, t-value 5.207 and p-value 0.000, the relationship between perceived usefulness and the adoption of metaverse with β-value 0.233, t-value 4.017 and p-value 0.000, and the relationship between trust and adoption of a metaverse with β-value 0.192, t-value 3.589 and p-value 0.000. Results also show that the digital divide moderates the relation between perceived ease of use and adopting the metaverse having β-value 0.078, t-value 1.848 and p-value 0.032. Similarly, the findings also show that the digital divide does not moderate the relationships of perceived usefulness and trust with adopting the metaverse. Moreover, the meta culture also does not moderate the relationships of perceived ease of use, usefulness, and trust with adopting the metaverse. The study contributes to theoretical research on adopting a metaverse in healthcare by examining various factors necessary for its development. It also provides guidelines for the developers and adopters of suitable metaverse technology.

A novel sequential structure for lightweight multi-scale feature learning under limited available images

Although multi-scale feature learning can improve the performances of deep models, its parallel structure quadratically increases the model parameters and causes deep models to become larger and larger when enlarging the receptive fields (RFs). This leads to deep models easily suffering from over-fitting issue in many practical applications where the available training samples are always insufficient or limited. In addition, under this limited situation, although lightweight models (with fewer model parameters) can effectively reduce over-fitting, they may suffer from under-fitting because of insufficient training data for effective feature learning. In this work, a lightweight model called Sequential Multi-scale Feature Learning Network (SMF-Net) is proposed to alleviate these two issues simultaneously using a novel sequential structure of multi-scale feature learning. Compared to both deep and lightweight models, the proposed sequential structure in SMF-Net can easily extract features with larger RFs for multi-scale feature learning only with a few and linearly increased model parameters. The experimental results on both classification and segmentation tasks demonstrate that our SMF-Net only has 1.25M model parameters (5.3% of Res2Net50) with 0.7G FLOPS (14.6% of Res2Net50) for classification and 1.54M parameters (8.9% of UNet) with 3.35G FLOPs (10.9% of UNet) for segmentation but achieves higher accuracy than SOTA deep models and lightweight models, even when the training data is very limited available.