Deep Learning Basics

Writing filed under Deep Learning Basics.

Deep Learning Basics

Small model choices still matter

A short note on the small model details that still shape behavior when systems move into production.

March 5 20254 min read

#activation functions #ReLU #neural networks

Deep Learning Basics

Backpropagation is bookkeeping with consequences

A slower explanation of gradients, loss, and weight updates for people who want the mechanism without the fog machine.

April 12 20246 min read

#backpropagation #gradient descent #training

Deep Learning Basics

An MLP is a stack of small calculations

A patient walkthrough of multi-layer perceptrons without pretending the acronym is more important than the arithmetic.

April 4 20245 min read

#mlp #neural networks #python

Deep Learning Basics

Batch processing stops the lesson from lying

Why running several inputs at once gives a more honest picture of what a model is doing.

March 28 20245 min read

#batching #numpy #deep learning

Deep Learning Basics

Hidden layers are just intermediate guesses

A plain-language explanation of hidden layers, why they help, and why the word hidden makes them sound stranger than they are.

March 21 20244 min read

#hidden layers #neural networks #teaching

Deep Learning Basics

Four neurons are enough to expose the wiring

A grounded walkthrough of a small neural network where the important part is the shape of the calculation.

March 14 20245 min read

#neural networks #layers #visualization

Deep Learning Basics

A single neuron is less mysterious when you run the numbers

A slower, more practical walkthrough of weights, bias, ReLU, and the first little model worth drawing by hand.

March 7 20245 min read

#neural networks #relu #teaching

Deep Learning Basics

Matrix multiplication is the first batch trick

A practical note on why neural network examples turn into matrices as soon as more than one example shows up.

March 4 20235 min read

#matrices #numpy #deep learning