Network Architecture62

What the inside of an AI model looks like. Neurons, layers, weights, activation functions, RNNs, LSTMs, parameters: what people actually mean when they say a model is "big" or "deep".

Level Beginner 15 Intermediate 30 Advanced 17

Activation Function

A built-in threshold that decides whether a signal passes on

Intermediate Attention

A way of deciding how much weight to give each input

LLM Intermediate Autoencoder

A structure that learns by shrinking data down and rebuilding it

Generative Intermediate Autoregressive

Rereads what it just wrote, then adds one more piece

Advanced Backpropagation

Tracing error backward to split blame across the network

Training Intermediate Bias Term

The default amount that's added no matter what the input is

Intermediate Black Box

An AI's decision process when the inside can't be seen

Ethics Beginner Browser AI

AI that runs inside a web page with nothing installed

Tools Beginner CNNConvolutional Neural Network

A neural network built to spot patterns in a photo, layer by layer

Vision Intermediate Compute

The total amount of calculation it takes to run a model once

Intermediate Convolution

Sliding a small tile across a photo to score it, spot by spot

Vision Intermediate Deep Learning

Machine learning that stacks processing steps many layers deep

Basics Beginner Depth vs Width

How many layers to stack versus how wide to make each one

Intermediate DQNDeep Q-Network

A neural network standing in for a table of expected scores

Training Advanced Dropout

Randomly resting part of a model during training

Training Intermediate Encoder-Decoder

A two-part design that reads with one half, writes with the other

LLM Intermediate Environmental Cost

The electricity and resources it takes to build and run AI

Ethics Beginner Feature Map

A picture that lays scan results out in their original spots

Vision Advanced Feed-Forward

A neural network structure where signals only flow forward

Intermediate Filter / Kernel

A small value tile that carries what to look for

Vision Intermediate GPU

A device that processes the same calculation many times at once

Basics Intermediate Gradient

The signal that says which way, and how far, to reduce error

Intermediate Hidden Layer

The middle layers between input and output that build features

Intermediate Latency

The time between sending a request and getting an answer back

Tools Beginner Layer

A computing stage made of neurons that all share the same input

Beginner Layer Normalization

A device that recalibrates the numbers' scale at every layer

Advanced Local LLM

Running an AI model directly on your own computer

Tools Beginner Logits

The raw score each candidate gets before becoming a probability

LLM Advanced LSTM

A recurrent network that uses gates to choose what to keep

Advanced Matrix Multiplication

Pairing up rows and columns, multiplying each pair, then summing

Intermediate Mixture of Experts

A model structure that switches on only the branches it needs

LLM Advanced Model Architecture

The blueprint that says how a model's layers stack and connect

Beginner Model Serving

Putting a finished model to work answering everyone's requests

Tools Intermediate Model Size

How many numbers a model is carrying

Beginner Multi-Head Attention

The same scene watched by several viewpoints at once

LLM Advanced Multilayer Perceptron

A basic neural network made of simple deciders stacked in layers

Intermediate Neural Network

Simple calculating units chained together in layers

Basics Beginner Neuron

A tiny computing unit that takes in many values and outputs one

Beginner On-Device AI

AI that a device's own hardware handles directly

Tools Beginner Open Weights

A model that hands out only the finished trained numbers

Tools Intermediate Parameter

A tuning dial inside a model whose value training decides

Beginner Perceptron

The first neural network — weighs inputs, then answers pass or fail

Intermediate Pooling

Shrinking a picture by keeping one representative value per region

Vision Intermediate Positional Encoding

A way of tagging each spot with its place in line

LLM Advanced Pruning

Cutting away unused connections to make a model lighter

Advanced Quantization

Coarsening the scale numbers are written on to make a model lighter

Intermediate ReLU

Blocks negative inputs at zero, passes positive ones through

Intermediate Residual Connection

A shortcut skipping a layer, carrying the original value through

Advanced RNNRecurrent Neural Network

A network that carries forward a running summary, word by word

Intermediate Self-Attention

Words in the same sentence checking in with each other

LLM Advanced Sequence-to-Sequence

Listens to the end, then rebuilds the message at a different length

Advanced Sigmoid

Squeezes any value into a smooth range between zero and one

Intermediate Softmax

A calculation that turns several scores into shares totaling 100%

LLM Intermediate Tensor

A bundle of numbers organized along several axes

Intermediate Transformer

An AI design where every word in a sentence looks at all the others

LLM Intermediate U-Net

Shrinks an image down, then grows it back while recovering position

Advanced Vanishing Gradient

When the fix-it signal fades away layer by layer, moving backward

Advanced Variational Autoencoder

An autoencoder that remembers things as a range, not a point

Generative Advanced Vector

A set of numbers for several items, written in a fixed order

LLM Intermediate Vision Transformer

Cutting a photo into pieces and treating it like text

Vision Advanced VRAM

The workspace where a graphics card lays out its numbers to compute

Beginner Weight

The learned multiplier on each input, deciding how much it counts