Reference for learners

Glossary

• artificial intelligence

• machine learning

• deep learning

• neural network

• convolutional neural network (CNN)

• recurrent neural network (RNN)

• accuracy

• epoch

• learning rate

• confusion matrix

• class imbalance

• overfitting

• hidden layer

External references

Here is a (non exhaustive) list of external resources for further study after this lesson:

Miscellaneous resources

• the difference between validation data and test data

• underfitting and overfitting

• Unbalanced data

• Unbalanced data in Keras

• Tensorflow Playground, for visualizing neural networks

• ChatGPT prompt engineering course

Some ML challenges or benchmarks

• https://mlcontests.com/

• Kaggle, machine learning competitions

• protein structure prediction

• prediction of protein-protein interactions

Some courses for deeper learning:

• Fast AI course: making neural nets uncool again

• Intro to Deep Learning with PyTorch, the course is quite intuitive

• Coursera courses by Andrew Ng:

  • AI for everyone, for beginners who won’t do ML projects but are courious about what AI really is and what AI can do

  • ML course and DL course, quite intensive courses for beginner/intermediate-level researchers who will do ML/DL projects

  • Structuring Machine Learning Projects, how to conduct ML projects with useful ML engineering strategies

  • Book on Machine Learning

• Book: Ian Goodfellow and Yoshua Bengio and Aaron Courville - Deep Learning. A really thorough, detailed (though math-heavy) book on everything (for example Generative Adverserial Networks or Autoencoders) you want to know about deep learning

• Book: Simon J.D. Prince - Understanding Deep Learning. A less dense and slightly more modern overview of deep learning with coding examples for each chapter.