In AI & ML
The process of taking a pre-trained model and further training it on a smaller, task-specific dataset to improve its performance on that task.
In Physics
The requirement that parameters of a physical theory be set to extremely precise values to match observed phenomena.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
In AI & ML
8Each in their own terms, from the easiest level.
Fei-Fei Li, Justin Johnson & Serena Yeung
Finetuning involves updating larger parts of a pre-trained network using a new dataset with a lower learning rate.Andrej Karpathy
The second stage of training where the base model is trained on high-quality Q&A conversations to become an assistant model.Jeremy Howard
Changing a model to behave based on specific documents that we have available.Sara Beery
Taking a pre-trained model and adapting it to a new task by initializing a second network with some or all of the original parameters and training it on new data.Phillip Isola
Fine-tuning initializes a second network with pre-trained weights and continues training on a new target data set.Melanie Mitchell
The process of further training a pre-existing machine learning model on specific data using consumer-grade hardware or advanced tools like PEFT and LoRA.Albert Jiang
The process of further training a pre-trained model on a specific dataset or domain to adapt it to particular tasks.
In Physics
1Nima Arkani-Hamed
Lectures that assume it
17The first 12 are shown.
- Deep Dive into Large Language Models: Pretraining to RLHF
- Deep Learning Software
- AI Seminar: Actionable Interpretability for Language Model Reasoning
- Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
- Decision Theoretic Foundations for Human-AI Collaboration
- Expanding What Robots Can Learn in the Real World
- Behind the Scenes of LLM Pre-training: StarCoder Use Case
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Inference Methods for Deep Learning
- Emerging Threats in LLM Privacy and Poisoning
- Retrieval Augmented Language Models
- From Large Language Models to Large Multimodal Models
Connections
37The lectures that define it or assume it, and the concepts next to it.
Concepts10
Show 4 moreShow fewer
Lectures27
- The Future of Fundamental Physics: Spacetime and Quantum Amplitudes
- Training Neural Networks II
- Introduction to Large Language Models
- Research Skills and Theoretical Physics
- A Hacker's Guide to Language Models
- Transfer Learning: Models
Show 21 moreShow fewer
- Demystifying Mixtral of Experts
- The Role of Rationality in Modern Robotics
- The Future of Artificial Intelligence
- Representation Learning: Reconstruction-Based
- Deep Dive into Large Language Models: Pretraining to RLHF
- Deep Learning Software
- AI Seminar: Actionable Interpretability for Language Model Reasoning
- Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
- Decision Theoretic Foundations for Human-AI Collaboration
- Expanding What Robots Can Learn in the Real World
- Behind the Scenes of LLM Pre-training: StarCoder Use Case
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Inference Methods for Deep Learning
- Emerging Threats in LLM Privacy and Poisoning
- Retrieval Augmented Language Models
- From Large Language Models to Large Multimodal Models
- Language Models: Prompting, Chain-of-Thought, and Instruction-Tuning
- Transformers in Vision: Tackling problems in Computer Vision
- Aligning Open Language Models
- Battle of the Big Bang: Alternative Cosmological Theories
- Overview of Transformers