Memory in LLMs - Weights and Activations

Memory in LLMs - Weights and Activations

AI Engineer via YouTube Direct link

The Knowledge Cutoff & Long-Tail Problem

1 of 8

1 of 8

The Knowledge Cutoff & Long-Tail Problem

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Memory in LLMs - Weights and Activations

Automatically move to the next video in the Classroom when playback concludes

  1. 1 The Knowledge Cutoff & Long-Tail Problem
  2. 2 Three Methods for Knowledge Injection Context, RAG, Weights
  3. 3 Limitations of "Full Context" Cost & Latency
  4. 4 The Transformer Bottleneck: Self-Attention Complexity
  5. 5 Context Rot: Performance degradation in long context
  6. 6 Q&A: The Return of Federated Learning
  7. 7 Q&A: Specialized Knowledge Models vs. Karpathy’s "Reasoning Engines"
  8. 8 Q&A: Temporal Information & Future Research

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.