Jotaro
84 posts















Day 2 of Teaching Loss Function & Initial Error Derivation Backpropagation Engine (Inc Sig × Loc Der) Output Layer Gradient Derivations Inter-Layer Error Propagation (Bridging L2 to L1) Layer 1 (Hidden Layer) Gradient Der Algorithmic Path Logic Raw Parameter Update Formulations

Day 1 here's what I taught > Nested Functions > Derivative of Nested Functions > What are Features / Observations as inputs > What exactly is weight nd Bias > How Linear Regression relates them > Graphically what it tells > Process of leading to Predictions

Deep Learning from Absolute Scratch No Pre requisites, if you've passed class 12 I've started teaching it from Today Onwards. With Maths First Approach Currently I have 3 students Comment if you wanna join in on this Journey !


Larp. Why are you using different color pens for a math problem





