🧠 Neural Networks - chris1 · Scour

Training a Transformer to Compose One Step Per Layer (and Proving It) 💬LLMs

lesswrong.com·4d

Deep-testing: the case of dependence detection 📐ML Theory

Learn&Drop: Fast Learning of CNNs based on Layer Dropping 🤖Machine Learning

Training Transformers as a Universal Computer 💬LLMs

Verification of Neural Networks (Lecture Notes) 💬LLMs

Comparative Evaluation of Modern Deep Learning Methodologies for Portfolio Optimization 🤖Machine Learning

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport 📐ML Theory

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks 🤖Machine Learning

Linear equivalence of nonlinear recurrent neural networks 📐ML Theory

Hierarchical adaptive control for real-time dynamic inference at the edge 🎮Reinforcement Learning

Speech Emotion Recognition Using MFCC Features and LSTM-Based Deep Learning Model 💬LLMs

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks 🤖Machine Learning

Encoded Forward Backward Stochastic Neural Network for High-Dimensional Backward Stochastic Differential Equations and Parabolic Partial Differential Equations 🎮Reinforcement Learning

SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions 📐ML Theory

Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence 💬LLMs

Evolutionary feature selection for spiking neural network pattern classifiers 🤖Machine Learning

The other paper that killed deep learning theory 📐ML Theory

lesswrong.com·3d

Large Language Models Explore by Latent Distilling 💬LLMs

A Functorial Formulation of Neighborhood Aggregating Deep Learning 📐ML Theory

NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics 🎮Reinforcement Learning

Sign up or log in to see more results

Log in to enable infinite scrolling