In this live stream, Siraj Raval attempes to beat a Kaggle Challenge — the $100,000 “TGS Salt Identification Challenge” using a combination of Google Colab, Conditional Random Fields, and neural networks! Expect some colorful exploratory data analysis, then model building and some Q&A.
One of the questions I get asked most frequently is how I so quickly changed from a “plain old software engineer” to “certified Data Scientist” as quickly as I did. While I do plan to write a book/shoot a video on the topic. In the meantime, enjoy this video from Siraj Raval where he shows the techniques he uses to study machine learning. It’s a fast moving field with lots of crazy math, so the old ways of learning just won’t cut it.
That includes living a healthy lifestyles, optimizing your learning environment, creating a personalized learning path, prioritizing effectively, and being an active learner. He demos the FAST technique, which you can use to help learn faster and more efficiently. While this with made with machine learning technology in mind, but these techniques can be used for any field.
Siraj Raval weighs in on Azure Machine Learning Studio.
How can blockchain technology help improve the supply chain?
All physical products must take a journey from the factory to the consumer and this journey is called the supply chain. Unfortunately, the path to the consumer isn’t straightforward, there are sometimes dozens of intermediaries involved in this process.
That includes quality assurance, drivers, procurement officers, etc. Blockchain acts as an immutable store of data, and removes the need for one or more third parties. It can help save both businesses and consumers time and money in this case. In this video Siraj Raval demonstrates a solidity app that tracks asset, talk about a real world example called SyncFab, and discuss the different ways blockchain can affect the supply chain.
Code for this video: https://github.com/syncfab/smartcontract
If you’re a reader of this blog, then you know that I have mentioned Alpha Go Zero before on a few occasions. However, I think this video by the incomparable Siraj Raval explains it best. Watch this video to get a technical overview of its neural components.
In case you didn’t already know, DeepMind’s AlphaGo Zero algorithm beat the best Go player in the world by training entirely by self-play. It played against itself repeatedly, getting better over time with no human gameplay input. AlphaGo Zero was a remarkable moment in AI history, a moment that will always be remembered.
How did OpenAI’s team of 5 neural networks manage to beat some of the world’s best DOTA 2 players?
Watch this video by Siraj Raval to learn how the team did it and what it means for AI research.
Siraj Rabal explains what is the best programming language to learn for machine learning?
Surprisingly, there are a lot options and naturally, a lot more opinions . In this video, Siraj describes the top 3, using code, animations, and data to validate my point. He does this all in eight minutes. Buckle up.
Siraj Raval has some advice for people looking to break into the Machine Learning/AI field for the first time with some resume tips.
What is back propagation, you ask? Well, it’s our old friend gradient descent’s new name when it is applied to neural networks.
If that explanation doesn’t work for you, then check out this video, where Siraj Raval explains back propagation in a way only he can: in song. Best of all, aside from the sick beats, is that the source code from the video is available on GitHub.