Educational Cards

Learn from video content, text, and interactive tasks

Filters
Clear
Classification heads and probabilistic outputs

The output layer presents ten competing scores, one per digit. For probabilistic training we often...

Beginner Machine learning
Pedagogical edge cases: saturation, dead ReLUs, initialization

The closing interview contrasts historical sigmoid activations, motivated by biological on/off...

Beginner Machine learning
The cost function as a high-dimensional surface

Chapter 1 showed how a forward pass turns pixels into digit guesses; this chapter asks how those...

Beginner Machine learning
Learning rate as step size: fragile knob

The learning rate eta controls how far each descent step moves in weight space. Too small and...

Beginner Machine learning
Stochasticity: minibatches approximate the full-data gradient

Exact gradient descent recomputes nabla C using every training example each step. For MNIST that is...

Beginner Machine learning
Local minima, saddles, and plateaus

Zero gradient marks a critical point , but not every critical point is a desirable resting place. A...

Beginner Machine learning
Momentum and adaptive methods (conceptual)

Plain SGD uses only the current batch gradient. Momentum maintains a velocity vector mathbfv that...

Beginner Machine learning
Bridge to automatic differentiation next

Gradient descent is useless without efficient partial derivatives. A naive finite-difference...

Beginner Machine learning
Backprop as structured chain rule on a DAG

Training needs partial C/partial w_i for every weight. Backpropagation organizes that bookkeeping...

Intermediate Machine learning
Memoization: forward activations feed backward formulas

Automatic differentiation frameworks tape the forward computation: each op records inputs and...

Intermediate Machine learning
Forward-mode vs reverse-mode: when each wins

Automatic differentiation has two standard modes. Forward mode seeds a perturbation on one input...

Intermediate Machine learning
Structured graphs: weight sharing and modular layers

Production networks are not bare MLP chains. Convolutions reuse the same kernel at every spatial...

Intermediate Machine learning