Related papers: Representational Drift and Learning-Induced Stabil…
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…
Magnetic skyrmions, as scalable and non-volatile spin textures, can dynamically interact with fields and currents, making them promising for unconventional computing. This paper presents a neuromorphic device based on skyrmion manipulation…
We consider a fully-connected network of leaky integrate-and-fire neurons with spike-timing-dependent plasticity. The plasticity is controlled by a parameter representing the expected weight of a synapse between neurons that are firing…
Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be…
A ubiquitous phenomenon observed throughout the primate hierarchical visual system is the sparsification of the neural representation of visual stimuli as a result of familiarization by repeated exposure, manifested as the sharpening of the…
Neural data compression has been shown to outperform classical methods in terms of $RD$ performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input…
Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is…
Backpropagation-optimized artificial neural networks, while precise, lack robustness, leading to unforeseen behaviors that affect their safety. Biological neural systems do solve some of these issues already. Unlike artificial models,…
The human brain represents objects in a way that is both invariant across instances and flexible enough to support different contexts and tasks. Yet it remains unknown how object representations are dynamically remapped as the same object…
We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…
The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel framework for investigating the formation and adaptation of…
We investigate a driven, one-dimensional system of colloidal particles in a periodically currogated narrow channel subject to a time-delayed feedback control. Our goal is to identify conditions under which the control induces oscillatory,…
Random walk methods are used to calculate the moments of negative image equilibrium distributions in synaptic weight dynamics governed by spike-timing dependent plasticity (STDP). The neural architecture of the model is based on the…
It has been discovered before (arXiv:2306.07676) that for the selectivity gain due to fluctuations in the process of primary odor reception by olfactory receptor neuron (ORN) there exists an optimal concentration of odors at which increased…
The Reward Prediction Error hypothesis proposes that phasic activity in the midbrain dopaminergic system reflects prediction errors needed for learning in reinforcement learning. Besides the well-documented association between dopamine and…
In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the agent performs a series of tasks drawn from distinct sets…
Photorealistic rendering of dynamic humans is an important ability for telepresence systems, virtual shopping, synthetic data generation, and more. Recently, neural rendering methods, which combine techniques from computer graphics and…
Subjective tinnitus (ST) is generally assumed to be a consequence of hearing loss (HL). In animal studies acoustic trauma can lead to behavioral signs of ST, in human studies ST patients without increased hearing thresholds were found to…
Artificial neural networks face the stability-plasticity dilemma in continual learning, while the brain can maintain memories and remain adaptable. However, the biological strategies for continual learning and their potential to inspire…
To better characterize the statistical processes underlying human decision-making, we performed experiments where human participants visualized fluctuations of physical nonequilibrium stationary states, and we analyzed responses in the…