AI is going to bring major shifts in society through developments in self-driving cars, medical image analysis, better medical diagnosis, and personalized medicine. But for many, it still remains a mystery.
deep learninghave made once again made AI the "next big thing" in the tech community. Unfortunately, deep learning is also one area of AI that is perhaps among the most misunderstood by the media and general public alike. We feel that it is important to demystify deep learning as much as possible so that more people are educated about what it can and can't do, and how it can be used for good.
Each fall, we guide a cohort of members through our deep learning curriculum, complete with in-person workshops. Members will then have a chance to implement this content by working on a variety of team projects in the spring.
All of our curriculum resources (slide presentations, IPython notebooks, etc.) are publicly available for viewing in our Github. We recommend downloading and working through the incomplete notebooks from each lesson locally. You can then compare your work to the completed notebooks. We have also uploaded our full lectures onto our YouTube channel. We hope that these materials will serve as helpful resources for anyone wanting to learn more about deep learning and artificial intelligence.
(Note that deep learning/machine learning is only one part of the much larger field of artificial intelligence. If you are interested, we recommend you look into other topics in AI as well!)
A brief overview of the most influential approaches to machine learning.
SectionsPart 1: k-Nearest Neighbors Part 2: Linear Regression Part 3: Logistic Regression Part 4: Support Vector Machines Part 5: Decision Trees Part 6: Naive Bayes
This lesson discusses much of the surface level theory that goes into a neural network. From this theory, you should gain a good understanding of how basic neural networks work, which will then allow you to work on actual implementations.
SectionsPart 1: Architecture Part 2: Training Part 3: Optimization
There are many advantages to varying the design of neural network architecture to suit a task's nature. In this lesson, we discuss common approaches to working with image and time-series data.
SectionsPart 1: Convolutional Neural Networks Part 2: Recurrent Neural Networks Part 3: Attention & Transformers Part 4: Generative Adversarial Networks
We’re compiling a list of some exciting topics within machine learning (and AI in general) that you may want to check out. Note that this is not by any means a comprehensive list of advanced topics in AI/machine learning — this is simply a list of active research areas that we think you should know about, and may hopefully serve as a valuable starting point for branching out into more specific fields.
SectionsPart 1: Transfer Learning Part 2: Reinforcement Learning
We're compiling a list of interesting and influential papers that we recommend you check out, if you're interested.