Comparing Generalization in Learning with Limited Numbers of Exemplars: Transformer vs. RNN in Attractor Dynamics

ChatGPT, a widely-recognized large language model (LLM), has recently gained substantial attention for its performance scaling, attributed to the billions of web-sourced natural language sentences used for training. Its underlying architecture, Transformer, has found applications across diverse fields, including video, audio signals, and robotic movement. %The crucial question this raises concerns the Transformer's generalization-in-learning (GIL) capacity. However, this raises a crucial question about Transformer's generalization in learning (GIL) capacity. Is ChatGPT's success chiefly due to the vast dataset used for training, or is there more to the story? To investigate this, we compared Transformer's GIL capabilities with those of a traditional Recurrent Neural Network (RNN) in tasks involving attractor dynamics learning. For performance evaluation, the Dynamic Time Warping (DTW) method has been employed. Our simulation results suggest that under conditions of limited data availability, Transformer's GIL abilities are markedly inferior to those of RNN.

Habits and goals in synergy: a variational Bayesian framework for behavior

How to behave efficiently and flexibly is a central problem for understanding biological agents and creating intelligent embodied AI. It has been well known that behavior can be classified as two types: reward-maximizing habitual behavior, which is fast while inflexible; and goal-directed behavior, which is flexible while slow. Conventionally, habitual and goal-directed behaviors are considered handled by two distinct systems in the brain. Here, we propose to bridge the gap between the two behaviors, drawing on the principles of variational Bayesian theory. We incorporate both behaviors in one framework by introducing a Bayesian latent variable called "intention". The habitual behavior is generated by using prior distribution of intention, which is goal-less; and the goal-directed behavior is generated by the posterior distribution of intention, which is conditioned on the goal. Building on this idea, we present a novel Bayesian framework for modeling behaviors. Our proposed framework enables skill sharing between the two kinds of behaviors, and by leveraging the idea of predictive coding, it enables an agent to seamlessly generalize from habitual to goal-directed behavior without requiring additional training. The proposed framework suggests a fresh perspective for cognitive science and embodied AI, highlighting the potential for greater integration between habitual and goal-directed behaviors.

Human-Robot Kinaesthetic Interaction Based on Free Energy Principle

The current study investigated possible human-robot kinaesthetic interaction using a variational recurrent neural network model, called PV-RNN, which is based on the free energy principle. Our prior robotic studies using PV-RNN showed that the nature of interactions between top-down expectation and bottom-up inference is strongly affected by a parameter, called the meta-prior, which regulates the complexity term in free energy.The study also compares the counter force generated when trained transitions are induced by a human experimenter and when untrained transitions are induced. Our experimental results indicated that (1) the human experimenter needs more/less force to induce trained transitions when $w$ is set with larger/smaller values, (2) the human experimenter needs more force to act on the robot when he attempts to induce untrained as opposed to trained movement pattern transitions. Our analysis of time development of essential variables and values in PV-RNN during bodily interaction clarified the mechanism by which gaps in actional intentions between the human experimenter and the robot can be manifested as reaction forces between them.

Morphological Wobbling Can Help Robots Learn

We propose to make the physical characteristics of a robot oscillate while it learns to improve its behavioral performance. We consider quantities such as mass, actuator strength, and size that are usually fixed in a robot, and show that when those quantities oscillate at the beginning of the learning process on a simulated 2D soft robot, the performance on a locomotion task can be significantly improved. We investigate the dynamics of the phenomenon and conclude that in our case, surprisingly, a high-frequency oscillation with a large amplitude for a large portion of the learning duration leads to the highest performance benefits. Furthermore, we show that morphological wobbling significantly increases exploration of the search space.

Initialization of Latent Space Coordinates via Random Linear Projections for Learning Robotic Sensory-Motor Sequences

Robot kinematics data, despite being a high dimensional process, is highly correlated, especially when considering motions grouped in certain primitives. These almost linear correlations within primitives allow us to interpret the motions as points drawn close to a union of low-dimensional linear subspaces in the space of all motions. Motivated by results of embedding theory, in particular, generalizations of Whitney embedding theorem, we show that random linear projection of motor sequences into low dimensional space loses very little information about structure of kinematics data. Projected points are very good initial guess for values of latent variables in generative model for robot sensory-motor behaviour primitives. We conducted series of experiments where we trained a recurrent neural network to generate sensory-motor sequences for robotic manipulator with 9 degrees of freedom. Experimental results demonstrate substantial improvement in generalisation abilities for unobserved samples in the case of initialization of latent variables with random linear projection of motor data over initialization with zero or random values. Moreover, latent space is well-structured wherein samples belonging to different primitives are well separated from the onset of training process.

Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments

We show that goal-directed action planning and generation in a teleological framework can be formulated using the free energy principle. The proposed model, which is built on a variational recurrent neural network model, is characterized by three essential features. These are that (1) goals can be specified for both static sensory states, e.g., for goal images to be reached and dynamic processes, e.g., for moving around an object, (2) the model can not only generate goal-directed action plans, but can also understand goals by sensory observation, and (3) the model generates future action plans for given goals based on the best estimate of the current state, inferred using past sensory observations. The proposed model is evaluated by conducting experiments on a simulated mobile agent as well as on a real humanoid robot performing object manipulation.

Active Inference in Robotics and Artificial Agents: Survey and Challenges

Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning. Recently, it has been shown to be a promising approach to the problems of state-estimation and control under uncertainty, as well as a foundation for the construction of goal-driven behaviours in robotics and artificial agents in general. Here, we review the state-of-the-art theory and implementations of active inference for state-estimation, control, planning and learning; describing current achievements with a particular focus on robotics. We showcase relevant experiments that illustrate its potential in terms of adaptation, generalization and robustness. Furthermore, we connect this approach with other frameworks and discuss its expected benefits and challenges: a unified framework with functional biological plausibility using variational Bayesian inference.

Sensory attenuation develops as a result of sensorimotor experience

The brain attenuates its responses to self-produced exteroceptions (e.g., we cannot tickle ourselves). Is this phenomenon, known as sensory attenuation, enabled innately, or is it acquired through learning? For decades, theoretical and biological studies have suggested related neural functions of sensory attenuation, such as an efference copy of the motor command and neuromodulation; however, the developmental aspect of sensory attenuation remains unexamined. Here, our simulation study using a recurrent neural network, operated according to a computational principle called free-energy minimization, shows that sensory attenuation can be developed as a free-energy state in the network through learning of two distinct types of sensorimotor patterns, characterized by self-produced or externally produced exteroceptive feedback. Simulation of the network, consisting of sensory (proprioceptive and exteroceptive), association, and executive areas, showed that shifts between these two types of sensorimotor patterns triggered transitions from one free-energy state to another in the network. Consequently, this induced shifts between attenuating and amplifying responses in the sensory areas. Furthermore, the executive area, proactively adjusted the precision of the prediction in lower levels while being modulated by the bottom-up sensory prediction error signal in minimizing the free-energy, thereby serving as an information hub in generating the observed shifts. We also found that innate alterations in modulation of sensory-information flow induced some characteristics analogous to schizophrenia and autism spectrum disorder. This study provides a novel perspective on neural mechanisms underlying emergence of perceptual phenomena and psychiatric disorders.

Goal-Directed Planning by Reinforcement Learning and Active Inference

What is the difference between goal-directed and habitual behavior? We propose a novel computational framework of decision making with Bayesian inference, in which everything is integrated as an entire neural network model. The model learns to predict environmental state transitions by self-exploration and generating motor actions by sampling stochastic internal states ${z}$. Habitual behavior, which is obtained from the prior distribution of ${z}$, is acquired by reinforcement learning. Goal-directed behavior is determined from the posterior distribution of ${z}$ by planning, using active inference which optimizes the past, current and future ${z}$ by minimizing the variational free energy for the desired future observation constrained by the observed sensory sequence. We demonstrate the effectiveness of the proposed framework by experiments in a sensorimotor navigation task with camera observations and continuous motor actions.