中文
相关论文

相关论文: Brain-Inspired Machine Intelligence: A Survey of N…

200 篇论文

Artificial and natural neural network models are a new toolkit which could be potentially have been used for clarifying of complex brain functions. To attend this goal, such models need to be neurobiologically realistic. However, although…

神经元与认知 · 定量生物学 2022-07-08 Arsenii Onuchin

Although the currently popular deep learning networks achieve unprecedented performance on some tasks, the human brain still has a monopoly on general intelligence. Motivated by this and biological implausibility of deep learning networks,…

神经元与认知 · 定量生物学 2019-09-10 Cengiz Pehlevan , Dmitri B. Chklovskii

Artificial Intelligence has looked into biological systems as a source of inspiration. Although there are many aspects of the brain yet to be discovered, neuroscience has found evidence that the connections between neurons continuously grow…

神经与进化计算 · 计算机科学 2020-10-29 Javier Lopez Randulfe , Leon Bonde Larsen

This workshop explores the interface between cognitive neuroscience and recent advances in AI fields that aim to reproduce human performance such as natural language processing and computer vision, and specifically deep learning approaches…

Plasticity circuits in the brain are known to be influenced by the distribution of the synaptic weights through the mechanisms of synaptic integration and local regulation of synaptic strength. However, the complex interplay of…

神经与进化计算 · 计算机科学 2021-04-26 Giorgia Dellaferrera , Stanislaw Wozniak , Giacomo Indiveri , Angeliki Pantazi , Evangelos Eleftheriou

Despite the striking successes of deep neural networks trained with gradient-based optimization, these methods differ fundamentally from their biological counterparts. This gap raises key questions about how nature achieves robust,…

机器学习 · 计算机科学 2025-10-15 Mattia Scardecchia

The brain is a remarkably capable and efficient system. It can process and store huge amounts of noisy and unstructured information using minimal energy. In contrast, current artificial intelligence (AI) systems require vast resources for…

神经与进化计算 · 计算机科学 2023-06-16 Michalis Pagkalos , Roman Makarov , Panayiota Poirazi

In the rapid evolution of next-generation brain-inspired artificial intelligence and increasingly sophisticated electromagnetic environment, the most bionic characteristics and anti-interference performance of spiking neural networks show…

神经与进化计算 · 计算机科学 2023-09-11 Lyuyang Sima , Joseph Bucukovski , Erwan Carlson , Nicole L. Yien

In this work, a conceptual bio-inspired parallel and distributed learning framework for the emergence of general intelligence is proposed, where agents evolve through environmental rewards and learn throughout their lifetime without…

神经与进化计算 · 计算机科学 2020-09-23 Sidney Pontes-Filho , Stefano Nichele

We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made toward understanding…

神经与进化计算 · 计算机科学 2022-06-29 Samuel Schmidgall , Joe Hays

Biological neural networks learn complex behaviors from sparse, delayed feedback using local synaptic plasticity, yet the mechanisms enabling structured credit assignment remain elusive. In contrast, artificial recurrent networks solving…

神经元与认知 · 定量生物学 2025-12-12 Dimitra Maoutsa

The field of artificial intelligence faces significant challenges in achieving both biological plausibility and computational efficiency, particularly in visual learning tasks. Current artificial neural networks, such as convolutional…

机器学习 · 计算机科学 2024-09-27 Jacobo Ruiz , Manas Gupta

The pursuit of creating artificial intelligence (AI) mirrors our longstanding fascination with understanding our own intelligence. From the myths of Talos to Aristotelian logic and Heron's inventions, we have sought to replicate the marvels…

神经元与认知 · 定量生物学 2024-11-26 Nima Dehghani , Michael Levin

With recent and rapid advancements in artificial intelligence (AI), understanding the foundation of purposeful behaviour in autonomous agents is crucial for developing safe and efficient systems. While artificial neural networks have…

人工智能 · 计算机科学 2025-08-12 Aswin Paul , Moein Khajehnejad , Forough Habibollahi , Brett J. Kagan , Adeel Razi

The human brain is a complex system that is fascinating scientists since a long time. Its remarkable capabilities include categorization of concepts, retrieval of memories and creative generation of new examples. At the same time, modern…

无序系统与神经网络 · 物理学 2024-10-10 Enrico Ventura

Temporal credit assignment is crucial for learning and skill development in natural and artificial intelligence. While computational methods like the TD approach in reinforcement learning have been proposed, it's unclear if they accurately…

人工智能 · 计算机科学 2023-07-18 Thuy Ngoc Nguyen , Chase McDonald , Cleotilde Gonzalez

Inspired by the natural nervous system, synaptic plasticity rules are applied to train spiking neural networks with local information, making them suitable for online learning on neuromorphic hardware. However, when such rules are…

神经与进化计算 · 计算机科学 2022-02-28 J. Lu , J. J. Hagenaars , G. C. H. E. de Croon

Learning depends on changes in synaptic connections deep inside the brain. In multilayer networks, these changes are triggered by error signals fed back from the output, generally through a stepwise inversion of the feedforward processing…

神经元与认知 · 定量生物学 2021-01-05 William F. Podlaski , Christian K. Machens

Understanding how recurrent neural circuits can learn to implement dynamical systems is a fundamental challenge in neuroscience. The credit assignment problem, i.e. determining the local contribution of each synapse to the network's global…

神经元与认知 · 定量生物学 2017-08-08 Alireza Alemi , Christian Machens , Sophie Denève , Jean-Jacques Slotine

We provide a comprehensive review of the existing literature on memory-augmented GNNs. We review these works through the lens of psychology and neuroscience, which has several established theories on how multiple memory systems and…

机器学习 · 计算机科学 2023-07-18 Guixiang Ma , Vy A. Vo , Theodore Willke , Nesreen K. Ahmed