archive
Every paper Pith has read. Search by title, abstract, or pith.
554 papers in cs.NE · page 1
-
UniSpike bundles spikes to cut neuromorphic traffic 1.93 times
UniSpike: Accelerating Spiking Neural Networks on Neuromorphic Systems via Eliminating Address Redundancy
-
Hysteretic attention reaches Turing completeness in constant depth
Preisach Attention: A Hysteretic Model of Sequential Memory
-
Spiking nets add dynamic expert routing with binary spikes only
SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks
-
Vector rewards produce diverse LLM outputs that raise search scores
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
-
Quantum genetic optimization improves anomaly detection accuracy
Quantum Genetic Optimization for Negative Selection Algorithms in Anomaly Detection
-
Early visual alignment conserved across species but IT rankings diverge
Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology
-
Description length post-selection lifts GP regression accuracy
Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions
-
Spike timing distinguishes objects whose features are merely rearranged
Temporal Coding as a Substrate for Sensorimotor Object Inference: A Spiking Reinterpretation of Thousand Brains Architecture
-
Equal spacing uniquely maximizes Solow-Polasky diversity on intervals
Exact Uniform L1 Spacing for Solow-Polasky Diversity on Lines and Ordered Pareto Fronts
-
Physics laws inside neural nets speed up power-grid modeling
Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review
-
Dropout creates two scaling-law classes by activation type
Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
-
Deeper networks approximate structured functions with fewer parameters
Approximation Theory for Neural Networks: Old and New
-
XOR-and-shift over GF(2) meets Marcus's three cognitive pillars
How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields
-
XOR-shift over GF(2) enables variable binding and recursive structure
How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields
-
Transformer mutation evolves improved approximate multipliers
Genetic Programming with Transformer-Based Mutation for Approximate Circuit Design
-
Upper bounds fix premature convergence in mixed-integer ES
Convergence Analysis of Evolution Strategies for Mixed-Integer Optimization
-
MPC-limited evolutionary search meets optimization deadlines
Privacy-Preserving Distributed Optimization Under Time Constraints Using Secure Multi-Party Computation and Evolutionary Algorithms
-
ReRAM macro reaches 419 TOPS/W for edge neural inference
E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference
-
Weight decay separates memorization
Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics
-
Evolutionary code agents gain by recycling deleted lines
What Do Evolutionary Coding Agents Evolve?
-
Two antagonistic Bayesian processes set the optimal learning rate
Training Neural Networks with Optimal Double-Bayesian Learning
-
Photonic network learns and remembers via driven-dissipative dynamics
Reconfigurable Nonlinear Photonic Networks for In-Situ Learning and Memory Formation via Driven-Dissipative Dynamics
-
Chained multi-population GA outperforms rivals in feature selection
Multi-population Diversity-guided Genetic Algorithm for Feature Selection in Network Intrusion Detection
-
One LLM system optimizes text to beat specialists on six tasks
optimize_anything: A Universal API for Optimizing any Text Parameter
-
Hierarchical Gaussian filters close the gap in deep predictive coding
Closed-form predictive coding via hierarchical Gaussian filters
-
Optical pass checks 15 deepfake videos simultaneously
Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection
-
Total IPC of stationary systems bounds to readout count and predicts ML results
Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
-
Total capacity of stationary physical systems predicts ML performance
Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
-
Graph diffusion solver reaches 100% feasibility on multi-objective scheduling
GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization
-
Self-supervised local rules learn hidden data hierarchies
Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data
-
Firefly algorithm auto-clusters data without preset count
When Fireflies Cluster; Enhancing Automatic Clustering via Centroid-Guided Firefly Optimization
-
kNN graph with persistence merging locates more peaks in multimodal search
Mapping the Fitness Landscape: A Structure-Guided Approach to Multi-Modal Optimization
-
FPGA accelerator adds on-device learning to spiking networks
Spiker-LL: An Energy-Efficient FPGA Accelerator Enabling Adaptive Local Learning in Spiking Neural Networks
-
Safe natural gradient projects binary solutions to avoid risks
Adaptive Stochastic Natural Gradient Method for Safe Optimization on Binary Space
-
Bounds tie PDE solution regularity to neural operator discretization error
Stability and Discretization Error of State Space Model Neural Operators
-
VENs cut learning failure rate from 30 percent to 2 percent
Von Economo neurons enable reliable social skill acquisition in recurrent spiking neural networks: a computational account with clinical predictions
-
RL portfolio strategies compete with buy-and-hold in Euro Stoxx 50
Deep Reinforcement Learning Framework for Diversified Portfolio Management Across Global Equity Markets
-
MRFO with Levy flight trains ELMs to predict binary crystal formation energies
Evolutionary Extreme Learning Machine of ab-initio Energy Landscapes for Crystal Structure Prediction using Manta Ray Optimization with Levy Flight
-
Clockless FPGA circuits yield low-power spiking neuromorphic processors
Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip
-
Algorithm balances LLM prompt quality against running costs
MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization
-
NDC turns thermodynamic networks into universal function approximators
Thermodynamic Networks: Harnessing Non-Equilibrium Steady States for Computation
-
Symbolic regression yields multiple expressions by varying residual patterns
Diversified Residual Symbolic Regression
-
Brain model generalizes abstract structures with path integration
Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model
-
Co-evolution builds general algorithm portfolios for binary optimization
General-Purpose Co-Evolutionary Construction of Parallel Algorithm Portfolios for Multi-Objective Binary Optimization
-
Galois-field memory unifies hippocampus and causal reasoning
Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM
-
Galois-field memory unifies hippocampus and causal reasoning
Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM
-
Galois-field registers give deterministic substrate for hippocampal memory
Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM
-
Deterministic Galois-field memory bridges silicon and hippocampus
Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM
-
PyTorch code turns frozen LMs into architecture performance predictors
Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search
-
Dendritic CNNs reach 93% accuracy with 1500 parameters
Perforated Neural Networks for Keyword Spotting