What a neuron actually computes

After this lesson you can: Compute one neuron's output by hand: weights, sum, bias, activation.

First: The dot product, and why similarity is just an angle

Watch

• But what is a neural network? | Deep learning chapter 1 - 3Blue1Brown, 19 min. Visual, beginner-friendly concept framing from a trusted channel, ideal after dot products before training details.
• Neural Network Simply Explained | Deep Learning Tutorial 4 (Tensorflow2.0, Keras & Python) - codebasics, 11 min. Short practical explanation likely connects the neuron idea to code-oriented deep learning intuition.

Notes

An artificial neuron is a small numeric function, not a tiny brain cell. It takes several input numbers, multiplies each by a corresponding weight, adds those products together, adds one extra number called the bias, and then passes the result through an activation function. If you already understand dot products, the core computation is just a dot product plus a bias, followed by a simple nonlinear transformation.

Unlock the full lesson notes, the exercises and the graded checkpoint - ₹5,000 once.