AI & ML Quick Path

Part 4: Deep learning

Neural networks and how to train them, then the model families used for images, text, audio, generation, decision-making and connected data.

9 lessonsAbout 12 hours of study (estimate)0 of 9 completed in this browser

Key terms in this part (24)

Neural networks

  1. Neural networks in plain words

    Explain neurons, layers, activations and backpropagation in plain words, and train a small network in Python and C#.

    Intermediate1.5 hNeeds: How a model learns: loss, training and overfitting

  2. Training deep networks well

    Use batches, epochs, learning rates, optimisers, dropout, normalisation, early stopping, checkpoints and GPUs to train networks reliably.

    Intermediate1.5 hNeeds: Neural networks in plain words

Model families

  1. Computer vision: classification, detection and segmentation

    Explain convolutional networks, transfer learning, object detection, segmentation and vision transformers, and run a trained vision model from Python and C#.

    Intermediate1.5 hNeeds: Training deep networks well

  2. Text and sequences: tokens, embeddings and RNNs

    Explain how text becomes numbers (tokens and embeddings), how word vectors capture meaning, and how recurrent networks process sequences and why transformers replaced them.

    Intermediate75 minNeeds: Neural networks in plain words, Feature engineering: turning raw data into model inputs

  3. Transformers and attention

    Explain attention with queries, keys and values, the parts of a transformer block, and the three transformer families (encoder, decoder, encoder-decoder).

    Intermediate1.5 hNeeds: Text and sequences: tokens, embeddings and RNNs

  4. Generative models: autoencoders, GANs and diffusion

    Explain how autoencoders, variational autoencoders, GANs and diffusion models create new data, and when industry uses each.

    Advanced75 minNeeds: Computer vision: classification, detection and segmentation

  5. Speech and audio: recognition and text-to-speech

    Explain how audio becomes features, how speech recognition and text-to-speech work, and measure transcription quality with word error rate.

    Advanced60 minNeeds: Transformers and attention

  6. Reinforcement learning

    Explain agents, actions, rewards and policies, implement Q-learning and a policy-gradient agent, and connect reinforcement learning to how chat models are tuned.

    Advanced75 minNeeds: How a model learns: loss, training and overfitting

  7. Graph neural networks: learning from connections

    Represent data as nodes and edges, explain message passing, and classify nodes from very few labels using their neighbours.

    Advanced60 minNeeds: Neural networks in plain words