惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
CERT Recently Published Vulnerability Notes
博
博客园 - 【当耐特】
有赞技术团队
有赞技术团队
Hugging Face - Blog
Hugging Face - Blog
Cisco Talos Blog
Cisco Talos Blog
爱范儿
爱范儿
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
人人都是产品经理
人人都是产品经理
大猫的无限游戏
大猫的无限游戏
博
博客园 - 三生石上(FineUI控件)
Martin Fowler
Martin Fowler
量
量子位
Cyberwarzone
Cyberwarzone
腾
腾讯CDC
博
博客园 - Franky
T
The Blog of Author Tim Ferriss
U
Unit 42
Engineering at Meta
Engineering at Meta
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
小众软件
小众软件
酷 壳 – CoolShell
酷 壳 – CoolShell
G
GRAHAM CLULEY
L
LINUX DO - 最新话题
The Hacker News
The Hacker News
Security Latest
Security Latest
N
News and Events Feed by Topic
S
Schneier on Security
www.infosecurity-magazine.com
www.infosecurity-magazine.com
H
Hacker News: Front Page
Schneier on Security
Schneier on Security
O
OpenAI News
C
Cybersecurity and Infrastructure Security Agency CISA
月光博客
月光博客
美
美团技术团队
博
博客园_首页
V
V2EX
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
T
Tailwind CSS Blog
雷峰网
雷峰网
WordPress大学
WordPress大学
GbyAI
GbyAI
C
Cisco Blogs
I
InfoQ
L
LINUX DO - 热门话题
Simon Willison's Weblog
Simon Willison's Weblog
T
Tor Project blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
S
Securelist
F
Full Disclosure

cs.NE updates on arXiv.org

MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC Combining Trained Models in Reinforcement Learning Training Non-Differentiable Networks via Optimal Transport ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance Benchmarking local Hebbian learning rules for memory storage and prototype extraction Robust volatility updates for Hierarchical Gaussian Filtering Spiking Sequence Machines and Transformers Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks Attractor FCM Physical Foundation Models: Fixed hardware implementations of large-scale neural networks When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry Learning to Forget: Continual Learning with Adaptive Weight Decay Causal Learning with Neural Assemblies NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning Text-Utilization for Encoder-dominated Speech Recognition Models EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programming Analysis and Explainability of LLMs Via Evolutionary Methods Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs MAEO: Multiobjective Animorphic Ensemble Optimization for Scalable Large-scale Engineering Applications Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks Learn&Drop: Fast Learning of CNNs based on Layer Dropping Architecture-Induced Recoverability Bias in Differentiable Symbolic Regression Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen Structure-Guided Diffusion Model for EEG-Based Visual Cognition Reconstruction HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks Multi-Task Optimization over Networks of Tasks Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling Distributional Value Estimation Without Target Networks for Robust Quality-Diversity EvoJail: Evolutionary Diverse Jailbreak Prompt Generation for Large Language Models Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search Scalable Memristive-Friendly Reservoir Computing for Time Series Classification Large Language Models Exhibit Normative Conformity Prototype-Grounded Concept Models for Verifiable Concept Alignment ECG-Lens: Benchmarking ML & DL Models on PTB-XL Dataset What Makes a Bacterial Model a Good Reservoir Computer? Predicting Performance from Separability and Similarity Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networks Why Fine-Tuning Encourages Hallucinations and How to Fix It Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning Structure as Computation: Developmental Generation of Minimal Neural Circuits NEAT-NC: NEAT guided Navigation Cells for Robot Path Planning Neural architectures for resolving references in program code Diffusion Language Models for Speech Recognition A Dynamic-Growing Fuzzy-Neuro Controller, Application to a 3PSP Parallel Robot On the Use of Evolutionary Optimization for the Dynamic Chance Constrained Open-Pit Mine Scheduling Problem Analog Optical Inference on Million-Record Mortgage Data Shapley Value-Guided Adaptive Ensemble Learning for Explainable Financial Fraud Detection with U.S. Regulatory Compliance Validation Does Dimensionality Reduction via Random Projections Preserve Landscape Features? Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems Beyond LLMs, Sparse Distributed Memory, and Neuromorphics <A Hyper-Dimensional SRAM-CAM "VaCoAl" for Ultra-High Speed, Ultra-Low Power, and Low Cost> SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds Retinal Cyst Detection from Optical Coherence Tomography Images TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution Universal statistical signatures of evolution in artificial intelligence architectures Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit Evolutionary Token-Level Prompt Optimization for Diffusion Models Hierarchical Kernel Transformer: Multi-Scale Attention with an Information-Theoretic Approximation Analysis A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization OpenCLAW-P2P v7.0-P2PCLAW: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review v7.0 -- Mathematical Corrections & Ecosystem Developments Edition An Imbalanced Dataset with Multiple Feature Representations for Studying Quality Control of Next-Generation Sequencing Selectivity and Shape in the Design of Forward-Forward Goodness Functions Efficient Disruption of Criminal Networks through Multi-Objective Genetic Algorithms DarwinNet: An Evolutionary Network Architecture for Agent-Driven Protocol Synthesis EvoForest: A Novel Machine-Learning Paradigm via Open-Ended Evolution of Computational Graphs Evolving Multi-Channel Confidence-Aware Activation Functions for Missing Data with Channel Propagation Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models Optimized Architectures for Kolmogorov-Arnold Networks AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging Transformer Semantic Genetic Programming for d-dimensional Symbolic Regression Problems Efficient Vector Symbolic Architectures from Histogram Recovery Language Models Learn Universal Representations of Numbers and Here's Why You Should Care A Practitioner's Guide to Kolmogorov-Arnold Networks Symbolic Quantile Regression for the Interpretable Prediction of Conditional Quantiles PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems HiPreNets: High-Precision Neural Networks through Progressive Training Machine Learning as Iterated Belief Change a la Darwiche and Pearl Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents Learning Evolution via Optimization Knowledge Adaptation Frame forecasting in cine MRI using the PCA respiratory motion model: comparing recurrent neural networks trained online and transformers P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization
Factorization tricks for LSTM networks
Oleksii Kuchaiev, Boris Ginsburg · 2017-03-31 · via cs.NE updates on arXiv.org

We present two simple ways of reducing the number of parameters and accelerating the training of large Long Short-Term Memory (LSTM) networks: the first one is "matrix factorization by design" of LSTM matrix into the product of two smaller matrices, and the second one is partitioning of LSTM matrix, its inputs and states into the independent groups. Both approaches allow us to train large LSTM networks significantly faster to the near state-of the art perplexity while using significantly less RNN parameters.

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。