archive
Every paper Pith has read. Search by title, abstract, or pith.
554 papers in cs.NE · page 5
-
Symmetry-constrained evolution finds near-marginal neural fields
Neuro-evolutionary stochastic architectures in gauge-covariant neural fields
-
Kernel memories resist quantization but fail on pruning
Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory
-
Kernel Hopfield nets resist quantization but not pruning
Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory
-
Evolutionary loop generates adaptable jailbreak prompts
EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models
-
One Hebbian module after Swin-Tiny's final stage tops few-shot accuracy
Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition
-
LLMs optimize best via local refinement and search localization
What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
-
Parallel memristive reservoirs beat Mamba with 21x faster training
Scalable Memristive-Friendly Reservoir Computing for Time Series Classification
-
LLMs shift answers to fit the group
Large Language Models Exhibit Normative Conformity
-
Neutral evolution builds interlocking protein complexity
Neutrally Evolving Interlocking Complexity in the Quandary Den
-
Portfolios of solvers beat the virtual best single algorithm
Similarity-based Portfolio Construction for Black-box Optimization
-
Magnitude of dominated sets is strictly Pareto compliant
The Magnitude of Dominated Sets: A Pareto Compliant Indicator Grounded in Metric Geometry
-
Simple MOEA loses speed on large combinatorial problems
On Scalability of Multi-Objective Evolutionary Algorithms on Combinatorial Optimisation Problems
-
Evolution tweaks quantized weights for higher accuracy
Evolutionary fine tuning of quantized convolution-based deep learning models
-
Bound splits GP symbolic regression into structure and constant terms
On the Generalization Bounds of Symbolic Regression with Genetic Programming
-
Search finds monotone functions with nonlinearity above majority
Monotone but Exciting: On Evolving Monotone Boolean Functions with High Nonlinearity
-
Inertia term lets Ising machines update all spins in parallel
A fully parallel densely connected probabilistic Ising machine with inertia for real-time applications
-
Spike sparsity fails to lower latency or energy on Jetson GPU
When Spike Sparsity Does Not Translate to Deployed Cost: VS-WNO on Jetson Orin Nano
-
Optimizer finds best blue-green setups using full flood simulations
Optimising Urban Flood Resilience
-
Visual prototypes let humans verify and fix concept alignment in AI
Prototype-Grounded Concept Models for Verifiable Concept Alignment
-
Visual prototypes ground concepts for direct inspection and fixes
Prototype-Grounded Concept Models for Verifiable Concept Alignment
-
Convolution cuts recurrent SNN parameters by 99%
Combining Convolution and Delay Learning in Recurrent Spiking Neural Networks
-
This paper benchmarks traditional machine learning and deep learning models for…
ECG-Lens: Benchmarking ML & DL Models on PTB-XL Dataset
-
Bacterial growth curves classify nonlinear patterns as reservoirs
What Makes a Bacterial Model a Good Reservoir Computer? Predicting Performance from Separability and Similarity
-
Markov-switched swarm optimizer runs 2.3x faster than CMA-ES
Frenetic Cat-inspired Particle Optimization: a Markov state-switching hybrid swarm optimizer with application to cardiac digital twinning
-
Swarm optimizer beats baselines for hypergraph influence maximization
Enhancing Discrete Particle Swarm Optimization for Hypergraph-Modeled Influence Maximization
-
Leak term in RNNs yields regular grids and better path integration
Impact of leaky dynamics on predictive path integration accuracy in recurrent neural networks
-
Spiking network halves error in converter parameter estimates
Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networks
-
Self-distillation reduces hallucinations from fine-tuning new facts
Why Fine-Tuning Encourages Hallucinations and How to Fix It
-
Symmetric grids lift photonic AI use by 6X
Towards Topology-Aware Very Large-Scale Photonic AI Accelerators
-
Diverse policy archives boost continual RL adaptability
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
-
Developmental rules yield circuit that learns MNIST in single epoch
Structure as Computation: Developmental Generation of Minimal Neural Circuits
-
Navigation cells guide NEAT for dynamic robot path planning
NEAT-NC: NEAT guided Navigation Cells for Robot Path Planning
-
Multitasking Pareto run solves several submodular problems at once
Analysis of Multitasking Pareto Optimization for Monotone Submodular Problems
-
Iterative reuse beats from-scratch solving for changing TSP time windows
On the Use of Iterative Problem Solving for the Traveling Salesperson Problem with Changing Time Window Constraints
-
New models resolve code references 10 times longer with 42% less error
Neural architectures for resolving references in program code
-
DNN-guided PSO tracks moving optima with smaller swarms
Deep Neural Network-guided PSO for Tracking a Global Optimal Position in Complex Dynamic Environment
-
Diffusion language models boost ASR accuracy with joint decoding
Diffusion Language Models for Speech Recognition
-
Fuzzy-neural controller cuts computation for 3PSP robot
A Dynamic-Growing Fuzzy-Neuro Controller, Application to a 3PSP Parallel Robot
-
Neural networks keep firing after external input stops
Modeling of Self-sustained Neuron Population without External Stimulus
-
Membrane multiplicative noise silences spiking networks most
General aspects of internal noise in spiking neural networks
-
Execution semantics turn brain models into usable digital twins
From Brain Models to Executable Digital Twins: Execution Semantics and Neuro-Neuromorphic Systems
-
Tailored rewards boost greedy packing for fixed tours
Greedy Approaches for Packing While Travelling with Deterministic and Stochastic Constraints
-
Diversity repair outperforms re-evaluation in dynamic mine scheduling
On the Use of Evolutionary Optimization for the Dynamic Chance Constrained Open-Pit Mine Scheduling Problem
-
Task connectivity boosts stability and generalization
Attention to task structure for cognitive flexibility
-
Optical computer reaches 94.6% on 5.8M mortgage records
Analog Optical Inference on Million-Record Mortgage Data
-
SHAP agreement sets per-transaction weights for top fraud scores
Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation
-
Random projections distort most ELA landscape features
Does Dimensionality Reduction via Random Projections Preserve Landscape Features?
-
Simulation model demonstrates nonrandom non-Lamarckian mutation
An abstract model of nonrandom, non-Lamarckian mutation in evolution using a multivariate estimation-of-distribution algorithm
-
Separation condition yields geometric convergence for dense memory
Algorithmic Analysis of Dense Associative Memory: Finite-Size Guarantees and Adversarial Robustness
-
NCAs form periodic attractors early
Stability and Geometry of Attractors in Neural Cellular Automata