English
Related papers

Related papers: Error-based or target-based? A unifying framework …

200 papers

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…

Neurons and Cognition · Quantitative Biology 2017-08-08 Alireza Alemi , Christian Machens , Sophie Denève , Jean-Jacques Slotine

The firing dynamics of biological neurons in mathematical models is often determined by the model's parameters, representing the neurons' underlying properties. The parameter estimation problem seeks to recover those parameters of a single…

Neurons and Cognition · Quantitative Biology 2022-10-05 Long Le , Yao Li

The plasticity of the conduction delay between neurons plays a fundamental role in learning. However, the exact underlying mechanisms in the brain for this modulation is still an open problem. Understanding the precise adjustment of…

Neural and Evolutionary Computing · Computer Science 2020-11-19 Alireza Nadafian , Mohammad Ganjtabesh

Spikes are the currency in central nervous systems for information transmission and processing. They are also believed to play an essential role in low-power consumption of the biological systems, whose efficiency attracts increasing…

Neural and Evolutionary Computing · Computer Science 2020-05-05 Qiang Yu , Shenglan Li , Huajin Tang , Longbiao Wang , Jianwu Dang , Kay Chen Tan

We describe a mechanism for biological learning and adaptation based on two simple principles: (I) Neuronal activity propagates only through the network's strongest synaptic connections (extremal dynamics), and (II) The strengths of active…

Disordered Systems and Neural Networks · Physics 2009-10-31 Per Bak , Dante R Chialvo

Although different learning systems are coordinated to afford complex behavior, little is known about how this occurs. This article describes a theoretical framework that specifies how complex behaviors that might be thought to require…

Artificial Intelligence · Computer Science 2015-03-27 Yanping Liu , Erik D. Reichle

We propose two frameworks to deal with problem settings in which both structured and unstructured data are available. Structured data problems are best solved by traditional machine learning models such as boosting and tree-based…

Machine Learning · Computer Science 2023-03-01 Andrea Treviño Gavito , Diego Klabjan , Jean Utke

We address the problem of learning feedback control where the controller is a network constructed solely of deterministic spiking neurons. In contrast to previous investigations that were based on a spike rate model of the neuron, the…

Neurons and Cognition · Quantitative Biology 2018-09-27 Tae Seung Kang , Arunava Banerjee

Spiking neural networks have been referred to as the third generation of artificial neural networks where the information is coded as time of the spikes. There are a number of different spiking neuron models available and they are…

Neural and Evolutionary Computing · Computer Science 2011-09-14 Evangelos Stromatias

Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent…

Neural and Evolutionary Computing · Computer Science 2016-10-31 Brian Gardner , André Grüning

Model selection is a problem that has occupied machine learning researchers for a long time. Recently, its importance has become evident through applications in deep learning. We propose an agreement-based learning framework that prevents…

Machine Learning · Computer Science 2018-06-05 Emmanouil Antonios Platanios

The timing of individual neuronal spikes is essential for biological brains to make fast responses to sensory stimuli. However, conventional artificial neural networks lack the intrinsic temporal coding ability present in biological…

Neural and Evolutionary Computing · Computer Science 2020-11-18 Iulia M. Comsa , Krzysztof Potempa , Luca Versari , Thomas Fischbacher , Andrea Gesmundo , Jyrki Alakuijala

The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, target networks notoriously require additional memory and delay…

Machine Learning · Computer Science 2026-03-02 Théo Vincent , Yogesh Tripathi , Tim Faust , Abdullah Akgül , Yaniv Oren , Melih Kandemir , Jan Peters , Carlo D'Eramo

This work is concerned with solving neural network-based feedback controllers efficiently for optimal control problems. We first conduct a comparative study of two prevalent approaches: offline supervised learning and online direct policy…

Optimization and Control · Mathematics 2024-04-10 Yue Zhao , Jiequn Han

Meta-learning algorithms aim to learn two components: a model that predicts targets for a task, and a base learner that quickly updates that model when given examples from a new task. This additional level of learning can be powerful, but…

Machine Learning · Computer Science 2020-11-05 Janarthanan Rajendran , Alex Irpan , Eric Jang

Spiking Neural Networks are powerful computational modelling tools that have attracted much interest because of the bioinspired modelling of synaptic interactions between neurons. Most of the research employing spiking neurons has been…

Neural and Evolutionary Computing · Computer Science 2019-03-05 Huanneng Qiu , Matthew Garratt , David Howard , Sreenatha Anavatti

Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli.…

Neural and Evolutionary Computing · Computer Science 2020-08-18 Brian Gardner , André Grüning

Targeted Learning is a subfield of statistics that unifies advances in causal inference, machine learning and statistical theory to help answer scientifically impactful questions with statistical confidence. Targeted Learning is driven by…

Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from…

Neural and Evolutionary Computing · Computer Science 2017-11-21 Hesham Mostafa , Vishwajith Ramesh , Gert Cauwenberghs

Brains learn to represent information from a large set of stimuli, typically by weak supervision. Unsupervised learning is therefore a natural approach for exploring the design of biological neural networks and their computations.…

Neurons and Cognition · Quantitative Biology 2025-10-17 Roy Urbach , Elad Schneidman