Training Trains Internship
Student login
← Deep Learning learning path
Deep Learning · Module 1 of 10

What is deep learning?

Deep learning uses many-layered neural networks to learn from data.

📖 Key ideas

  1. Deep learning is a subset of machine learning using neural networks with many layers.
  2. It learns features automatically from raw data (images, text, audio).
  3. Needs lots of data and compute (GPUs).
  4. Powers image recognition, speech, translation and chatbots.
  5. Frameworks: PyTorch, TensorFlow/Keras, JAX.
💡 Real-life example: Deep learning is a factory with many floors: each floor refines the product a bit more.
Neural networkLayers of connected artificial neurons
DeepMany hidden layers
GPUProcessor good at parallel maths
Feature learningLearning useful representations automatically