English
Related papers

Related papers: An Online Learning Algorithm for Neuromorphic Hard…

200 papers

In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks. The new algorithm combines deterministic and…

Neural and Evolutionary Computing · Computer Science 2009-11-11 Aristoklis D. Anastasiadis , George D. Magoulas

Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning…

Machine Learning · Computer Science 2023-12-19 Jifan Zhang , Shuai Shao , Saurabh Verma , Robert Nowak

Application of neuromorphic edge devices for control is limited by the constraints on gradient-free online learning and scalability of the hardware across control problems. This paper introduces a synaptic Q-learning algorithm for the…

Systems and Control · Electrical Eng. & Systems 2025-11-21 Shreyan Banerjee , Aasifa Rounak , Vikram Pakrashi

What types of numeric representations emerge in neural systems, and what would a satisfying answer to this question look like? In this work, we interpret Neural Network (NN) solutions to sequence based number tasks using a variety of…

Machine Learning · Computer Science 2025-08-19 Satchel Grant , Noah D. Goodman , James L. McClelland

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and…

Machine Learning · Computer Science 2025-02-04 Javier Bernal , Jose Torres-Jimenez

Re-training a deep learning model each time a single data point receives a new label is impractical due to the inherent complexity of the training process. Consequently, existing active learning (AL) algorithms tend to adopt a batch-based…

Machine Learning · Computer Science 2023-12-19 Yunpyo An , Suyeong Park , Kwang In Kim

This paper presents the Never Ending Open Learning Adaptive Framework (NEOLAF), an integrated neural-symbolic cognitive architecture that models and constructs intelligent agents. The NEOLAF framework is a superior approach to constructing…

Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is…

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional non-related data, how…

Machine Learning · Computer Science 2020-08-07 Yayong Li , Jie Yin , Ling Chen

We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We…

Machine Learning · Computer Science 2024-05-16 Maxime Heuillet , Ola Ahmad , Audrey Durand

Brains need to predict how the body reacts to motor commands. It is an open question how networks of spiking neurons can learn to reproduce the non-linear body dynamics caused by motor commands, using local, online and stable learning…

Neurons and Cognition · Quantitative Biology 2017-11-30 Aditya Gilra , Wulfram Gerstner

This paper introduces an active learning (AL) framework for anomalous sound detection (ASD) in machine condition monitoring system. Typically, ASD models are trained solely on normal samples due to the scarcity of anomalous data, leading to…

Sound · Computer Science 2024-08-13 Tuan Vu Ho , Kota Dohi , Yohei Kawaguchi

This paper presents a residual-informed machine learning approach for replacing algebraic loops in equation-based Modelica models with neural network surrogates. A feedforward neural network is trained using the residual (error) of the…

Machine Learning · Computer Science 2025-10-13 Felix Brandt , Andreas Heuermann , Philip Hannebohm , Bernhard Bachmann

Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-understandable/black-box nature. Thus, this work presents a novel SME-AGOL to address such problems. Firstly, Sequential…

Robotics · Computer Science 2025-05-19 Arthicha Srisuchinnawong , Poramate Manoonpong

Spiking neural networks (SNNs) are bio-plausible computing models with high energy efficiency. The temporal dynamics of neurons and synapses enable them to detect temporal patterns and generate sequences. While Backpropagation Through Time…

Neural and Evolutionary Computing · Computer Science 2023-07-24 Zhenhang Zhang , Jingang Jin , Haowen Fang , Qinru Qiu

With the increasing penetration of renewable energy sources, growing demand variability, and evolving grid control strategies, accurate and efficient load modeling has become a critical yet challenging task. Traditional methods, such as…

Systems and Control · Electrical Eng. & Systems 2025-03-11 Ding Lin , Han Guo , Jianhui Wang , Meng Yue , Tianqiao Zhao

Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand. In contrast, the hyperparameters and learning algorithms of networks of neurons in the brain, which they aim to emulate, have been optimized…

Neural and Evolutionary Computing · Computer Science 2019-06-11 Thomas Bohnstingl , Franz Scherr , Christian Pehle , Karlheinz Meier , Wolfgang Maass

Temporal coding is one approach to representing information in spiking neural networks. An example of its application is the location of sounds by barn owls that requires especially precise temporal coding. Dependent upon the azimuthal…

Neurons and Cognition · Quantitative Biology 2014-01-24 Thomas Pfeil , Anne-Christine Scherzer , Johannes Schemmel , Karlheinz Meier

A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models. Solve-training framework uses the neural network as the ansatz of the solution map and train the network…

Numerical Analysis · Mathematics 2020-10-16 Yingzhou Li , Jianfeng Lu , Anqi Mao

The last decade has seen the parallel emergence in computational neuroscience and machine learning of neural network structures which spread the input signal randomly to a higher dimensional space; perform a nonlinear activation; and then…

Neural and Evolutionary Computing · Computer Science 2013-06-11 Jonathan Tapson , Andre van Schaik