ML Studio

Link to YouTube channel: Machine Learning Studio

Deep Learning Series playlist

Video	Description
Video 1: Top 10 Activaiton Functions	Giving a review of activation functions
Video 2: A Review of Top NN Optimizers	A review of top 16 optimization algorithms for training neural networks

Attention mechanism & Transformers playlist

Video	Description
Video 1: Marix Multiplication Concept Explained	Linear algebra concepts (pre-requisite to attention mechanism)
Video 2: Self-Attention Using Scaled Dot-Product Approach	Understanding the self-attention mechanism, and intro to scaled dot-product attention
Video 3: A Dive Into Multihead Attention, Self-Attention and Cross-Attention	Multihead Attention
Video 4: Transformer Architecture	Transformer
Video 5: PostLN, PreLN and ResiDual Transformers	LayerNorm in Transformer
Video 6: Variants of Multi-head Attention: MQA and GQA	MQA and GQA
Video 7: Efficient Self-Attention	Reducing Complexity
Video 8: Implementing Linear-Complexity Attention	Implementing Linear-Attention in PyTorch
Video 9: Introducing a new seriws on Vision Transformers	Introduction and outline of Vision Transformers series
Video 10: Self Attention in Image Domain	Self-Attention in Image domain: Non-Local Module
Video 11: Relative Self-Attention Explained	Mechanics of Relative Self-Attention
Video 12: Evolution of Self-Attention in Vision	Attention-Augmented Conv. (AANet), Stand-Alone Self-Attention (SASA), and Stand-Alone Axial Attention (SAAA)