Machine LearningLesson 17Free preview
ML Deep Learning
This lesson is part of A.I. · All levels
Summary
Deep learning uses a neural network made up of multiple layers of neurons. Each neuron adds the input weighed, adds bias, and then passes the result to an activation function like a sigmoid or ReLU. The large number of layers makes the network capable of studying highly complex patterns.
Key points
- Neural networks consist of input layers, hidden layers, and output layers.
- Each neuron counts the number of inputs weighed plus bias.
- The nonlinear activation function (sigmoid, ReLU) allows networks to model complex patterns.
- Deep learning is a neural network with many layers of hidden learning.
- Overfitting happens when the model memorizes the data training.
Full lesson
Code examples and quizzes
Full lessons, code examples, and quizzes are available to subscribers. 5 questions.