However, none of these models were examined in memory tasks.

Humans have a remarkable ability to rapidly generalize to new tasks that is difficult to reproduce in artificial learning systems.Compositionality has been proposed as a key mechanism supporting generalization in humans, but evidence of its neural implementation and impact on behavior is still scarce. Here we study the computational properties associated with compositional generalization in both humans and artificial neural networks (ANNs) on a highly compositional task. First, we identified behavioral signatures of compositional generalization in humans, along with their neural correlates using whole-cortex functional magnetic resonance imaging (fMRI) data. Next, we designed pretraining paradigms aided by a procedure we term primitives pretraining to endow compositional task elements into ANNs. We found that ANNs with this prior knowledge had greater correspondence with human behavior and neural compositional signatures. Importantly, primitives pretraining induced abstract internal representations, excellent zero-shot generalization, and sample-efficient learning. Moreover, it gave rise to a hierarchy of abstract representations that matched human fMRI data, where sensory rule abstractions emerged in early sensory areas, and motor rule abstractions emerged in later motor areas. Our findings give empirical support to the role of compositional generalization in humans behavior, implicate abstract representations as its neural implementation, and illustrate that these representations can be embedded into ANNs by designing simple and efficient pretraining procedures.

However, none of these models were examined in memory tasks.

Figure taken and adapted from [38]. Different works consider different properties. Compared to backpropagation (BP), predictive coding (PC) allows for more flexibility in the definition, training, and evaluation of the model. The experiments reported in this paper show the best results achieved on each specific task and, as a consequence, only the effects of a specific set of hyperparameters. Feedforward networks (left) simply overfit (i.e., reproduce without performing any modification) the input samples, despite being unrelated to the training data.

Humans have a remarkable ability to rapidly generalize to new tasks that is difficult to reproduce in artificial learning systems.Compositionality has been proposed as a key mechanism supporting generalization in humans, but evidence of its neural implementation and impact on behavior is still scarce. Here we study the computational properties associated with compositional generalization in both humans and artificial neural networks (ANNs) on a highly compositional task. First, we identified behavioral signatures of compositional generalization in humans, along with their neural correlates using whole-cortex functional magnetic resonance imaging (fMRI) data. Next, we designed pretraining paradigms aided by a procedure we term primitives pretraining to endow compositional task elements into ANNs. We found that ANNs with this prior knowledge had greater correspondence with human behavior and neural compositional signatures.

The goal of perception is to infer the hidden states in the hierarchical process by which sensory data are generated. Human behavior is consistent with the optimal statistical solution to this problem in many tasks, including cue combination and orientation detection. Understanding the neural mechanisms underlying this behavior is of particular importance, since probabilistic computations are notoriously challenging. Here we propose a simple mechanism for Bayesian inference which involves averaging over a few feature detection neurons which fire at a rate determined by their similarity to a sensory stimulus. This mechanism is based on a Monte Carlo method known as importance sampling, commonly used in computer science and statistics.

Most complex behaviors appear to be governed by internal moti(cid:173) vational states or drives that modify an animal's responses to its environment. It is therefore of considerable interest to understand the neural basis of these motivational states. Drawing upon work on the neural basis of feeding in the marine mollusc Aplysia, we have developed a heterogeneous artificial neural network for con(cid:173) trolling the feeding behavior of a simulated insect. We demonstrate that feeding in this artificial insect shares many characteristics with the motivated behavior of natural animals.

This study investigates a population decoding paradigm, in which the estimation of stimulus in the previous step is used as prior knowledge for consecutive decoding. We analyze the decoding accu(cid:173) racy of such a Bayesian decoder (Maximum a Posteriori Estimate), and show that it can be implemented by a biologically plausible recurrent network, where the prior knowledge of stimulus is con(cid:173) veyed by the change in recurrent interactions as a result of Hebbian learning.