training - Concepts

Explore concepts tagged with "training"

Total concepts: 14

Concepts

Instruction Tuning - A fine-tuning technique that trains language models to follow natural language instructions by learning from examples of instruction-response pairs.
Reinforcement Learning from Human Feedback (RLHF) - A training technique that aligns LLM outputs with human preferences by using human feedback to guide model behavior.
Model Collapse - The degradation of AI model quality when trained on synthetic data generated by other AI models, causing progressive loss of diversity and accuracy.
Reward Model - A neural network trained to predict human preferences, used to provide a scalar reward signal for optimizing language model behavior in RLHF.
Constitutional AI - AI training method using a set of principles (constitution) to guide model behavior and self-improvement.
Knowledge Distillation - A model compression technique where a smaller student model is trained to reproduce the behavior and outputs of a larger, more capable teacher model.
Attention Gym - Regular practices for building and maintaining attentional fitness and focus capacity.
Attention Training - Practices designed to improve attentional capacity, control, and flexibility.
Direct Preference Optimization - A simplified alternative to RLHF that fine-tunes language models directly on human preference data without training a separate reward model.
Stress Inoculation - Controlled exposure to manageable stress to build tolerance and coping skills for future challenges.
Reinforcement Learning - A machine learning paradigm where an agent learns to make decisions by taking actions in an environment and receiving rewards or penalties as feedback.
Multi-Task Learning - A machine learning approach where a single model is trained on multiple related tasks simultaneously, leveraging shared representations to improve generalization.
Federated Learning - A distributed machine learning approach where models are trained across multiple decentralized devices or servers holding local data, without exchanging raw data.
Fine-Tuning - Customizing pre-trained AI models by training them further on specific data or tasks.

← Back to all concepts