On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “Neuro-inspired”

A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive codingcs.LG

A neuro-inspired architecture learns without supervision using clustering and predictive coding.

problem Achieving continual learning without supervision.

method Neuro-inspired architecture based on online clustering and hierarchical predictive coding.

result The architecture achieves continual learning without supervision.

neural networks unsupervised learning continual learning clustering predictive coding

2018-10-22abs ↗pdf ↗

Mod-DeepESN: Modular Deep Echo State Networkcs.LG

Mod-DeepESN improves echo state networks for complex, multi-scale tasks.

problem Efficiency in solving complex, multi-scale temporal tasks.

method Incorporates intrinsic plasticity into a modular deep echo state network architecture.

result Significantly outperforms state-of-the-art for time series prediction tasks.

Echo State Networks Neuro-inspired Recurrent Neural Networks Modular Design Time Series Prediction

2018-08-01abs ↗pdf ↗

GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Datacs.LG

GOTabPFN improves tabular model performance with compact tokenization for HDLSS data.

problem Making tabular models effective for high-dimensional, low-sample size data without retraining.

method Introducing Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to create compact meta-features.

result GOTabPFN improves stability and accuracy in tabular benchmarks with compact tokenization.

tabular models HDLSS data compact tokenization Neuro-Inspired Subunit Compression Graph-guided Ordering

2026-06-03abs ↗pdf ↗

Unsupervised Learning in Neuromemristive Systemscs.ET

Neuromemristive systems (NMSs) currently represent the most promising platform to achieve energy efficient neuro-inspired computation. However, since the research field is less than a decade old, there are still countless algorithms and design paradigms to be explored within these systems. One particular domain that re…

2016-01-27abs ↗pdf ↗

Sample-Efficient Reinforcement Learning with Maximum Entropy Mellowmax Episodic Controlcs.LG

MEMEC improves sample efficiency in reinforcement learning.

problem Lack of sample efficiency in reinforcement learning.

method Proposes MEMEC, a Boltzmann policy with state-dependent temperature for more principled exploration.

result MEMEC outperforms other methods on classic RL environments and Atari games.

reinforcement learning sample efficiency episodic control maximum entropy Boltzmann policy

2019-11-21abs ↗pdf ↗

Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-meanscs.LG

Efficiently stores and retrieves past states for faster learning in reinforcement learning.

problem Data inefficiency and memory limitations in reinforcement learning.

method Dynamic online k-means for state clustering and prioritization.

result Dynamic online k-means improves performance with smaller memory sizes.

reinforcement learning episodic control memory efficiency state clustering k-means algorithm

2019-11-21abs ↗pdf ↗

Better Safe than Sorry: Evidence Accumulation Allows for Safe Reinforcement Learningcs.LG

Accumulator module improves reinforcement learning by delaying decisions based on evidence.

problem Incomplete information, limited sensing, and stochastic environments lead to risky decisions.

method Integrates evidence for each action, delays action until confident, using dynamic competition.

result Accumulator module outperforms traditional reinforcement learning methods in a guessing game.

reinforcement learning dynamic decision making evidence accumulation uncertainty safe action selection

2018-09-24abs ↗pdf ↗

RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systemscs.LG

Neuro-inspired RL solves complex control problems with fewer controllers.

problem Solving nonlinear control problems with unknown dynamics efficiently.

method Hierarchical RL framework combining limb coordination and reinforcement learning.

result Local LQR controllers combined with a reinforcement learner solve global nonlinear problems.

Reinforcement Learning Hierarchical Control Neurobiological Inspiration Linear Quadratic Regulators Nonlinear Control

2019-03-07abs ↗pdf ↗