Skip to content
Felix Notes
Search
Ctrl
K
Cancel
GitHub
X
Select theme
Dark
Light
Auto
Introduction
Artificial Intelligence
Representation Learning
Continual learning
Representation collapse
Masking strategies
Evaluation
Masked Autoencoders
MoCo
SimCLR
JEPA
Deep Learning
Overview
Numpy
Tensor
Autograd
Regularization
PyTorch
Distributed training
PyTorch internals
Bigram
MLP
CNN
Transformer
Large Language Models
Overview
Efficient Multi-head Attention
Interpretability
VietAI Zero to Hero
Assessment Prep
Python
North Star Problems
Interview Prep
System Design
Systems
CS 2011: Introduction to Machine Organization and Assembly Language
CS 2303: System Programming Concepts
CS 3013: Operating Systems
CS 3431: Database Systems I
CS 4432: Database Systems II
CS 3516: Computer Networking
CS 4401: Software Security Engineering
CS 4513: Distributed Systems
Distributed Systems
General CS
CS 61A Berkeley
Week 1
Week 2
Week 3
Week 4
Week 5
Week 6
Week 7
Week 8
Week 9
Week 10
Week 11
Week 12
CS 1102: Accelerated Introduction to Program Design
CS 2103: Accelerated Object Oriented Design Concepts
CS 2223: Algorithms
Big-O Orange 14
CS 536: Programming Language Design
RBE 474x: Deep Learning for Perception
CS 541: Deep Learning
Web Development
WEB103 CodePath
The Twelve Factor App
Foundations
HTML & CSS
JavaScript
NodeJS
SvelteKit
MySQL
Docker
Design System
Music
MU 3002: Arranging and Orchestration
Guitar
GitHub
X
Select theme
Dark
Light
Auto
Bi-directional Encoder Representations from Transformers
Being able to identify
masked tokens
from its context requires deep understanding of the language.
Masking ratio: 15%