technique

Recurrent Neural Network

techniqueactiverecurrent-neural-network-ec78e7ab·2 events·first seen 28d ago

Aliases: Recurrent Neural Network

Co-occurring entities

Transformers Hugging Face RWKV Reinforcement Learning OpenAI RL²

More like this (12)

ResNet Feedforward Neural Networks Graph Neural Networks convolutional neural network Pretraining Recurrent Networks without Recurrence Spiking Neural Networks Relational Deep Learning neural network image classifiers Reversible Residual Layers OpenAI Red Teaming Network Superposition Model (neural networks)large neural network training

Recent events (2)

5Hugging Face Blog·28d ago·source ↗

Introducing RWKV - An RNN with the advantages of a transformer

Hugging Face introduces RWKV, a recurrent neural network architecture that claims to combine the parallelizable training of transformers with the efficient linear-time inference of RNNs. The model avoids the quadratic attention bottleneck of standard transformers while maintaining competitive performance. RWKV represents an alternative architectural direction to the dominant transformer paradigm for language modeling.

Frontier Model Releases Open Weights Progress Transformers Recurrent Neural Network Hugging Face +2 more

5Openai Blog·28d ago·source ↗

RL²: Fast Reinforcement Learning via Slow Reinforcement Learning

OpenAI published RL², a meta-reinforcement learning approach in which a slow outer RL process trains a recurrent neural network whose hidden state encodes a fast inner learning algorithm. The method allows agents to rapidly adapt to new tasks within a single episode by leveraging experience accumulated across many training tasks. This work is an early foundational contribution to meta-learning for RL, predating the modern agent and LLM era but relevant to understanding the intellectual lineage of in-context and few-shot learning in AI systems.

Agent and Tool Ecosystem Alignment and RLHF Recurrent Neural Network Reinforcement Learning OpenAI +1 more