English
Related papers

Related papers: Spikes as regularizers

200 papers

In the search for more sample-efficient reinforcement-learning (RL) algorithms, a promising direction is to leverage as much external off-policy data as possible. For instance, expert demonstrations. In the past, multiple ideas have been…

Machine Learning · Computer Science 2023-03-01 Jesus Bujalance Martin , Fabien Moutarde

Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from over-conservatism that suppresses high-value actions in the…

Machine Learning · Computer Science 2026-05-28 Jiaxin Zhao , Weihang Pan , Xun Liang , Binbin Lin

Reinforcement Learning (RL) provides a powerful framework for decision-making in complex environments. However, implementing RL in hardware-efficient and bio-inspired ways remains a challenge. This paper presents a novel Spiking Neural…

Neural and Evolutionary Computing · Computer Science 2023-08-09 Sergio F. Chevtchenko , Yeshwanth Bethi , Teresa B. Ludermir , Saeed Afshar

Hierarchical reinforcement learning (HRL) leverages temporal abstraction to efficiently tackle complex long-horizon tasks. However, HRL often collapses because the continual updates of the low-level primitive make earlier sub-goals issued…

Machine Learning · Computer Science 2025-08-19 Utsav Singh , Vinay P. Namboodiri

Spiking neural networks (SNNs) promise energy-efficient computation by mimicking biological neural dynamics, yet existing plasticity rules focus on isolated spike pairs and fail to leverage the synchronous activity patterns that drive…

Neural and Evolutionary Computing · Computer Science 2025-08-26 Yuchen Tian , Assel Kembay , Samuel Tensingh , Nhan Duy Truong , Jason K. Eshraghian , Omid Kavehei

We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded…

Machine Learning · Computer Science 2023-01-10 Gene Li , Junbo Li , Anmol Kabra , Nathan Srebro , Zhaoran Wang , Zhuoran Yang

Spiking neural networks (SNNs), particularly the single-spike variant in which neurons spike at most once, are considerably more energy efficient than standard artificial neural networks (ANNs). However, single-spike SSNs are difficult to…

Neural and Evolutionary Computing · Computer Science 2022-10-13 Luke Taylor , Andrew King , Nicol Harper

Inspired by the human brain's ability to adapt to new tasks without erasing prior knowledge, we develop spiking neural networks (SNNs) with dynamic structures for Class Incremental Learning (CIL). Our comparative experiments reveal that…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Wenyao Ni , Jiangrong Shen , Qi Xu , Huajin Tang

Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision-making on neuromorphic hardware by mimicking the event-driven dynamics of biological neurons. However, the discrete and non-differentiable nature of spikes leads…

Neural and Evolutionary Computing · Computer Science 2026-03-05 Zijie Xu , Xinyu Shi , Yiting Dong , Zihan Huang , Zhaofei Yu

Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approaches depend on human-curated problem-answer pairs and…

Artificial Intelligence · Computer Science 2026-03-03 Bo Liu , Leon Guertler , Simon Yu , Zichen Liu , Penghui Qi , Daniel Balcells , Mickel Liu , Cheston Tan , Weiyan Shi , Min Lin , Wee Sun Lee , Natasha Jaques

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes.…

Machine Learning · Computer Science 2025-04-10 Sanjit Neelam , Daniel Heinlein , Vaclav Cvicek , Akshay Mishra , Reiner Pope

Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To…

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Machine Learning · Computer Science 2020-12-22 Somjit Nath , Richa Verma , Abhik Ray , Harshad Khadilkar

We present a spike-based unsupervised regenerative learning scheme to train Spiking Deep Networks (SpikeCNN) for object recognition problems using biologically realistic leaky integrate-and-fire neurons. The training methodology is based on…

Neural and Evolutionary Computing · Computer Science 2016-02-05 Priyadarshini Panda , Kaushik Roy

Spiking neural networks have shown great promise for the design of low-power sensory-processing and edge-computing hardware platforms. However, implementing on-chip learning algorithms on such architectures is still an open challenge,…

Neural and Evolutionary Computing · Computer Science 2021-04-13 Matteo Cartiglia , Germain Haessig , Giacomo Indiveri

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Computation and Language · Computer Science 2026-05-12 Jyotin Goel , Souvik Maji , Pratik Mazumder

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual…

Machine Learning · Computer Science 2023-07-21 Wei Cong , Yang Cong , Gan Sun , Yuyang Liu , Jiahua Dong

Human feedback can greatly accelerate robot learning, but in real-world settings, such feedback is costly and limited. Existing human-in-the-loop reinforcement learning (HiL-RL) methods often assume abundant feedback, limiting their…

Robotics · Computer Science 2025-09-26 Anujith Muraleedharan , Anamika J H

Learning from interaction is the primary way that biological agents acquire knowledge about their environment and themselves. Modern deep reinforcement learning (DRL) explores a computational approach to learning from interaction and has…

Neural and Evolutionary Computing · Computer Science 2024-11-26 Duzhen Zhang , Tielin Zhang , Shuncheng Jia , Qingyu Wang , Bo Xu

ISAC enables pervasive monitoring, but modern sensing algorithms are often too complex for energy-constrained edge devices. This motivates the development of learning techniques that balance accuracy performance and energy efficiency.…

Neural and Evolutionary Computing · Computer Science 2026-02-09 Eleonora Cicciarella , Riccardo Mazzieri , Jacopo Pegoraro , Michele Rossi