English
Related papers

Related papers: Recurrent infomax generates cell assemblies, avala…

200 papers

Continual Text Classification (CTC) aims to continuously classify new text data over time while minimizing catastrophic forgetting of previously acquired knowledge. However, existing methods often focus on task-specific knowledge,…

Computation and Language · Computer Science 2025-05-28 Duzhen Zhang , Yong Ren , Chenxing Li , Dong Yu , Tielin Zhang

The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical to designing intelligent systems. Many approaches to continual learning rely on stochastic gradient descent and its variants that…

Machine Learning · Computer Science 2023-08-10 Sandeep Madireddy , Angel Yanguas-Gil , Prasanna Balaprakash

The brain is a highly reconfigurable machine capable of task-specific adaptations. The brain continually rewires itself for a more optimal configuration to solve problems. We propose a novel strategic synthesis algorithm for feedforward…

Artificial Intelligence · Computer Science 2021-04-22 Alastair Finlinson , Sotiris Moschoyiannis

The ability to store and manipulate information is a hallmark of computational systems. Whereas computers are carefully engineered to represent and perform mathematical operations on structured data, neurobiological systems perform…

Disordered Systems and Neural Networks · Physics 2020-05-05 Jason Z. Kim , Zhixin Lu , Erfan Nozari , George J. Pappas , Danielle S. Bassett

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the…

Machine Learning · Computer Science 2023-06-22 Depeng Li , Zhigang Zeng

Behavioral changes in animals and humans, as a consequence of an error or a verbal instruction, can be extremely rapid. Improvement in behavioral performances are usually associated in machine learning and reinforcement learning to synaptic…

Neurons and Cognition · Quantitative Biology 2025-03-12 Cristiano Capone , Luca Falorsi

In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the…

Computation and Language · Computer Science 2025-01-15 Bernal Jiménez Gutiérrez , Yiheng Shu , Yu Gu , Michihiro Yasunaga , Yu Su

Cells are often considered input-output devices that maximize the transmission of information by converting extracellular stimuli (input) via signaling pathways (communication channel) to cell behavior (output). However, in biological…

Cell Behavior · Quantitative Biology 2019-11-04 Gabriele Micali , Robert G. Endres

Biological neurons and their in-silico emulations for neuromorphic artificial intelligence (AI) use extraordinarily energy-efficient mechanisms, such as spike-based communication and local synaptic plasticity. It remains unclear whether…

Neural and Evolutionary Computing · Computer Science 2021-06-17 Timoleon Moraitis , Abu Sebastian , Evangelos Eleftheriou

Animals learn to predict external contingencies from experience through a process of conditioning. A natural mechanism for conditioning is stimulus substitution, whereby the neuronal response to a stimulus with no prior behavioral…

Neurons and Cognition · Quantitative Biology 2024-09-23 Pantelis Vafidis , Antonio Rangel

Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of…

Neural and Evolutionary Computing · Computer Science 2019-11-18 Dylan Richard Muir

Despite remarkable technological advances, AI systems may still benefit from biological principles, such as recurrent connectivity and energy-efficient mechanisms. Drawing inspiration from the brain, we present a biologically plausible…

Neurons and networks in the cerebral cortex must operate reliably despite multiple sources of noise. To evaluate the impact of both input and output noise, we determine the robustness of single-neuron stimulus selective responses, as well…

Neurons and Cognition · Quantitative Biology 2018-01-24 Ran Rubin , L. F. Abbott , Haim Sompolinsky

We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly…

Machine Learning · Computer Science 2019-06-06 Wachirawit Ponghiran , Gopalakrishnan Srinivasan , Kaushik Roy

Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms use undirected exploration, i.e., select random sequences of…

Machine Learning · Computer Science 2025-08-01 Bhavya Sukhija , Stelian Coros , Andreas Krause , Pieter Abbeel , Carmelo Sferrazza

This work presents a new algorithm for training recurrent neural networks (although ideas are applicable to feedforward networks as well). The algorithm is derived from a theory in nonconvex optimization related to the diffusion equation.…

Machine Learning · Computer Science 2016-02-08 Hossein Mobahi

A recurrent neural network with noisy input is studied analytically, on the basis of a Discrete Time Master Equation. The latter is derived from a biologically realizable learning rule for the weights of the connections. In a numerical…

Disordered Systems and Neural Networks · Physics 2009-10-31 M. Heerema , W. A. van Leeuwen

We investigate the performance of sparsely-connected networks of integrate-and-fire neurons for ultra-short term information processing. We exploit the fact that the population activity of networks with balanced excitation and inhibition…

Neurons and Cognition · Quantitative Biology 2007-05-23 Julien Mayor , Wulfram Gerstner

Finding relevant information from large document collections such as the World Wide Web is a common task in our daily lives. Estimation of a user's interest or search intention is necessary to recommend and retrieve relevant information…

Information Retrieval · Computer Science 2016-12-09 Manuel J. A. Eugster , Tuukka Ruotsalo , Michiel M. Spapé , Oswald Barral , Niklas Ravaja , Giulio Jacucci , Samuel Kaski

We consider the problem of autonomously learning reusable temporally extended actions, or options, in reinforcement learning. While options can speed up transfer learning by serving as reusable building blocks, learning reusable options for…

Machine Learning · Computer Science 2023-06-01 Yuji Kanagawa , Tomoyuki Kaneko