Deep Learning: More Layers, More Calculations

A neural network repeats simple calculations across many connected neurons. Add more layers or make layers wider, and the network gains more weights and biases—called parameters. Those parameters must be stored, learned during training, and used in calculations every time the model produces an answer.

More or wider layersMore neurons are connected.
More parametersMore weights and biases must be stored and learned.
More calculationsMore work is needed during training and every model run.
The key idea: deeper and wider networks can learn more complex patterns, but they require more memory, computation, time, and electrical power.
Network shape Inputs, hidden layers, and outputs determine how many weighted connections the model has.
Parameter cost Each new connection adds a weight; each neuron usually adds a bias.
Maths connection Neural networks repeat the basic idea of y = ax + b across every layer.
Learning example Change the network below and watch parameters and calculations grow immediately.

Change the network structure

Type layer sizes separated by commas. Example: 8, 16, 8
Cost message Your current network is small.
Loading...
  • Wider layers add many more connections.
  • More hidden layers increase depth.
  • Both usually increase training and inference cost.
  • For image or letter recognition, the input layer often grows quickly because each pixel can become an input value.

Cost summary

Layer sizes
-
Total parameters
-
Approx memory (FP32)
-
Relative compute cost
-
Depth
-
Approx weighted calculations per run
-
Parameter = weight + bias Weight is like a Bias is like b More parameters = more calculations More layers = more sequential stages

Parameters and y = ax + b

In traditional maths, a straight line is often written as y = ax + b. The a controls how strongly the input x changes the output y, and the b shifts the result up or down.

A neural network neuron uses the same idea, just repeated many times: each connection has a weight, and each neuron has a bias. During training, the network searches for useful values for those weights and biases.

Traditional: y = a*x + b One neuron: output = activation(w*x + b) Many inputs: output = activation(w1*x1 + w2*x2 + ... + b)

Network picture

Lines represent weighted connections. Nodes represent units. The picture is capped visually so large networks still stay easy to view.

Small deep learning example: letter recognition

Dark cell = pixel turned on
Every pixel is connected to the next layer
Blue glow = stronger active signal
Predicted letter
1. Input image A small grid stores the letter as pixel values.
2. Hidden layers Every input pixel connects to the next layer, even white pixels.
3. Output scores Each output node represents one possible letter.
4. Prediction The highest score becomes the recognised letter.
Example shown: the network reads a small pixel grid and predicts which letter it is.

Smallest useful network example

The smallest useful neural network can be just one input and one output neuron. It is not deep yet, but it uses the same parameter idea as larger networks: one weight and one bias. Here it predicts whether a student is likely to pass from the number of study hours.

Input: x = study hours Parameters learned by training: weight w = 2 bias b = -5 Neuron calculation: z = w*x + b score = sigmoid(z) Decision rule: if score >= 0.5, predict Pass otherwise, predict Not pass What sigmoid means: sigmoid(z) = 1 / (1 + e^(-z)) It squeezes any number into a score between 0 and 1. Example 1: x = 3 hours z = 2*3 - 5 = 1 score = sigmoid(1) score = 1 / (1 + e^(-1)) score = 1 / (1 + 0.37) = 0.73 result = Pass Example 2: x = 2 hours z = 2*2 - 5 = -1 score = sigmoid(-1) score = 1 / (1 + e^(1)) score = 1 / (1 + 2.72) = 0.27 result = Not pass Parameter count: 1 weight + 1 bias = 2 parameters
Study hours x z = 2*x - 5 sigmoid(z) Prediction
3 1 0.73 Pass
2 -1 0.27 Not pass
This is the same shape as y = ax + b: the weight is like a, the bias is like b, and sigmoid turns the raw result z into a probability-like score between 0 and 1.