Executive functions guide episodic memory to retrieve information essential for adaptive behavior. The prefrontal cortex achieves this by influencing hippocampal processing through anatomical projections targeting the entorhinal cortex and area CA1. However, most computational models of the hippocampus overlook this cognitive control, either neglecting it or implementing implausible direct connections to the hippocampus. This paper explores the contextual control of associative memory implemented by modern Hopfield networks, within a hippocampus-inspired autoencoder. Our experiments underscore the importance of proximity between prefrontal afferences and the locus of memory storage for efficient contextual modulation of episodic memory, challenging the standard model of hippocampal processing. These findings not only advance our understanding of higher-level cognition but also provide design principles for more adaptive machine learning algorithms.

Neural Episodic Control is a powerful reinforcement learning framework that employs a differentiable dictionary to store non-parametric memories. It was inspired by episodic memory on the functional level, but lacks a direct theoretical connection to the associative memory models generally used to implement such a memory. We first show that the dictionary is an instance of the recently proposed Universal Hopfield Network framework. We then introduce a continuous approximation of the dictionary readout operation in order to derive two energy functions that are Lyapunov functions of the dynamics. Finally, we empirically show that the dictionary outperforms the Max separation function, which had previously been argued to be optimal, and that performance can further be improved by replacing the Euclidean distance kernel by a Manhattan distance kernel. These results are enabled by the generalization capabilities of the dictionary, so a novel criterion is introduced to disentangle memorization from generalization when evaluating associative memory models.

Several popular sequence-based and pretrained language models have been found to be successful for text-driven prediction of brain activations. However, these models still lack long-term cognitive plausibility as well as insights on the underlying neural substrate mechanisms. This paper studies the influence of context representations of different language models such as sequence-based models: Long short-term memory networks (LSTMs) and ELMo, and popular pretrained Transformer language model (Longformer). In particular, we study how the internal hidden representations align with the brain activity observed via fMRI when the subjects listen to several narrative stories. We use brain imaging recordings of subjects listening to narrative stories to interpret word and sequence embeddings. We further investigate how the representations of language models layers reveal better semantic context during listening. Experiments across all language model representations provide the following cognitive insights: (i) the representations of LSTM cell states are better aligned with brain recordings than LSTM (hidden state), the cell state activity can represent more long-term information, (ii) the representations of ELMo and Longformer display a good predictive performance across brain regions for listening stimuli; (iii) Posterior Medial Cortex (PMC), Temporo-Parieto-Occipital junction (TPOJ), and Dorsal Frontal Lobe (DFL) have higher correlation versus Early Auditory (EAC) and Auditory Association Cortex (AAC).

How do children bootstrap language through noisy supervision? Most prior works focused on tracking co-occurrences between individual words and referents. We model cross-situational learning (CSL) at sentence level with few (1000) training examples. We compare reservoir computing (RC) and LSTMs on three datasets including complex robotic commands. For most experiments, reservoirs yield superior performance over LSTMs. Surprisingly, reservoirs demonstrate robust generalization when increasing vocabulary size: the error grows slowly. On the contrary, LSTMs are not robust: the number of hidden units needs to be dramatically increased to follow up vocabulary size increase, which is questionable from a biological or cognitive perspective. This suggests that that random projections used in RC helps to bootstrap generalization quickly. To our knowledge, this is a new result in developmental learning modelling. We analyse the evolution of internal representations during training of both recurrent networks and suggest why reservoir generalization seems more efficient.

Computer science offers a large set of tools for prototyping, writing, running, testing, validating, sharing and reproducing results; however, computational science lags behind. In the best case, authors may provide their source code as a compressed archive and they may feel confident their research is reproducible. But this is not exactly true. James Buckheit and David Donoho proposed more than two decades ago that an article about computational results is advertising, not scholarship. The actual scholarship is the full software environment, code, and data that produced the result. This implies new workflows, in particular in peer-reviews. Existing journals have been slow to adapt: source codes are rarely requested and are hardly ever actually executed to check that they produce the results advertised in the article. ReScience is a peer-reviewed journal that targets computational research and encourages the explicit replication of already published research, promoting new and open-source implementations in order to ensure that the original research can be replicated from its description. To achieve this goal, the whole publishing chain is radically different from other traditional scientific journals. ReScience resides on GitHub where each new implementation of a computational study is made available together with comments, explanations, and software tests.