Gentle introduction to deep learning

A brief introduction to what deep learning is about, applications of deep learning and learning methodologies.

Transcript

1. A gentle introduction to deep learning
2. Rajika Imal Software Engineer at 99X Technology @rajikaimal rajikaa@99x.lk
3. Artificial intelligence The theory and development of computer systems able to perform tasks requiring human level intelligence such as visual perception, speech recognition. - wikipedia
4. Machine learning Sub-field in artificial intelligence that uses statistical techniques to give computer systems the ability to learn. - wikipedia - machine learning mastery
5. Basics of machine learning • Supervised learning • Unsupervised learning • Reinforcement learning
6. Learning with labelled training data Example: • Classifying email as spam or ham. • Predicting the breed of a dog. Supervised learning - stats and bots
7. Unsupervised learning Self discovering patterns in unlabelled data Example: • Clustering news articles in Google news. - oracle blogs
8. Reinforcement learning Learning based on the reward given for actions performed. Example: • An agent playing atari. • Chess playing agent. - hackernoon
9. Deep learning Subfield in machine learning. A technique inspired by how the human brain works. Term deep learning was introduced in 1986 by Rina Dechter.
10. Fast forward to late 2000 • Big data • Huge compute power ◦ Advanced CPUs ◦ GPUs
11. Applications of deep learning • Autonomous vehicles. eg: Tesla autopilot • Translation applications • Image tagging • Text generation • Colorization of black and white images • Music generation Tesla autopilot: https://bit.ly/2fTmW13 Fifa playing NN: https://bit.ly/2O8vIIz Video surveillance: https://bit.ly/2meiNaR
12. Neuron A cell in human brain that carries electrical impulses.
13. General architecture - https://bit.ly/2OLRSp4
14. Gradient descent - wikipedia
15. Types of neural networks • Convolutional neural networks (CNN) • Recurrent neural networks (RNN) • Generative adversarial networks (GAN) • LSTM
16. Bottom up approach Starting with theoretical knowledge. • Linear algebra • Calculus • Statistics and probability
17. Top-down approach Starting from a framework and working towards creating models to be applied for sample scenarios. Example: • Spam detector • Image classifier to classify dogs and cats • Natural language generator for english Frameworks: • PyTorch, Tensorflow, Keras, Fast.ai
18. Mixed-approach Combining top-down and bottom-up approaches to gain knowledge about theoretical concepts as well as the current frameworks used by developers and researchers.
19. Career paths • Machine learning engineer • Data scientist • Research scientist
20. Platforms to learn deep learning • Kaggle • GitHub • Twitter • Fast.ai • Coursera
21. Who to follow? • Andrew Ng (Co-founder of Google brain / Coursera / Baidu AI) • Jeff Dean (Co-founder of Google brain) • Siraj Raval (School of AI / Content creator) • Andrew Trask (OpenMind) • Karpathy (Tesla) • Ian Goodfellow (Google brain) • Jeremy Howard (fast.ai)
22. Thank you!
23. Rajika Imal @rajikaimal rajikaa@99x.lk