I think this "machine learning for hackers" approach is just not enough. Oftentimes, you do need a solid theoretical/mathematical background. Most people seems to approach ML like they approach programming tools or libraries - learn just enough to get job done and move on.<p>I was studying machine learning from Andrew Ng's CS229 (the class videos are online. I think they date from 2008 or hereabout). There is no way you can progress beyond lecture 2 (out of 20) without a solid probability background. A solid background in probability/statistics probably means a good first course in Probability or maybe the first five chapters of "Statistical Inference" by Cassias and Berger. Similarly, for SVM, you need a solid background in Linear Algebra and so on. You probably also need a background Linear Optimization. Here are the recommendations by Prof. Michael Jordan <a href="https://news.ycombinator.com/item?id=1055389" rel="nofollow">https://news.ycombinator.com/item?id=1055389</a><p>Not a lot of people want to dive in this much. They have got things to do and who cares about proofs anyway. The thinking goes like "Most of the mathematics is abstracted away by libraries like scikit-learn. Let's get shit done.". Well, I think a lot of competitive advantage of Google/Facebook in ML is because they have staffed their engineering with people who have studied these things for years (by PhD). Compare that to flipkart's recommendations.<p>However, I don't think this problem is unique to ML/Data Science. It is equally bad in "Distributed systems". Let's use Docker, that's the future!
Thanks for sharing. Here's a set of deep learning resources I've found useful to give you a good theoretical background as well as start applying techniques to real world problems:<p>1. Intro deep learning, bit of theory and intuition building while applying it to a toy problem:<p><a href="http://neuralnetworksanddeeplearning.com/index.html" rel="nofollow">http://neuralnetworksanddeeplearning.com/index.html</a><p>2. A video series walkthrough on how to replicate some of the recent advances:<p><a href="http://course.fast.ai/lessons/lessons.html" rel="nofollow">http://course.fast.ai/lessons/lessons.html</a><p>3. More theoretical background:<p><a href="http://www.deeplearningbook.org/" rel="nofollow">http://www.deeplearningbook.org/</a><p>4. Tensorflow tutorials with practical applications:<p><a href="https://www.tensorflow.org/tutorials/" rel="nofollow">https://www.tensorflow.org/tutorials/</a><p>Specific applications:<p>Deep Learning for Vision:<p><a href="https://www.youtube.com/playlist?list=PLkt2uSq6rBVctENoVBg1TpCC7OQi31AlC" rel="nofollow">https://www.youtube.com/playlist?list=PLkt2uSq6rBVctENoVBg1T...</a><p>Deep Learning for NLP:<p><a href="https://www.youtube.com/playlist?list=PLIiVRB6G_w0i-uOoS6cDh_5nkUyxy_hxe" rel="nofollow">https://www.youtube.com/playlist?list=PLIiVRB6G_w0i-uOoS6cDh...</a>
> So I am doubling down on ML/DL.<p>The amount of free resources now available for learning machine learning/deep learning nowadays is robust and easy to comprehend. (indeed, Andrew Ng's Coursera class is very good). And running running ML code is even easier, with libraries like Tensorflow/Theano to abstract the ML gruntwork (and Keras to abstract the abstraction!)<p>I suspect that there may be machine learning knowledge <i>crash</i>, where the basics are repeated endlessly, but there is less <i>unique, real world application</i> of the knowledge learned. I've seen many Internet testimonials saying how "I followed an online tutorial and now I can classify handwritten digits, AI is the future!" The meme that Kaggle competitions are a metric of practical ML skill encourages budding ML enthusiasts to look at minimizing log-loss or maximizing accuracy <i>without considering time/cost tradeoffs</i>, which doesn't reflect real-world constraints.<p>Unfortunately, many successful real world applications of ML/DL are the ones <i>not</i> being instructed in tutorials as they are trade secrets (this is the case with "big data" literature, to my frustration). OpenAI is a good step toward transparency in the field, but that won't stop the ML-trivializing "this program can play Pong, AI is the future!" thought pieces (<a href="https://news.ycombinator.com/item?id=13256962" rel="nofollow">https://news.ycombinator.com/item?id=13256962</a>).
Distributed Systems and ML are probably two most interesting things that I have on the radar, that got me really scared to the point where I do not know from where to start, and most importantly for what?! Most of my free time (time I spent on personal projects) was writing physics simulation in Java, playing with Lisp and doing some backend development. Nothing amazing. Year and a half ago I got really interested into Operating systems (tried FreeBSD and blew my mind) and played with Docker. And at the end of this year, I am like:
"Ok Philip what shall I focus on for year to come?" And the thing is If I choose to go Ai route, I do not know from where to start (I consider my math background to be pretty good, I was studying EE before I dropped out after 2 years, and enrolled to CS, done all of the math courses which were pretty rough), Ai/ML looks interesting but it looks so high level to program and so abstract to understand. It's really looking like arcane magic to me. With Dist. Systems is that I have a feeling that is more "engineering" and "industrial" thing, where you can't do much by yourself at home, besides reading and writing some code in relevant languages about backend, sometimes lower level, and learning about systems and computer innards. And the third option was to go and play with Erlang/Elixir, which is most attractive since results will come pretty soon, and may be relevant form my interest in Distributed systems.
A counterpoint: Deep learning is currently hyped, making you not consider other techniques that might work better, or are simpler and work just as good. Deep learning might have a limited scope and turn out to be a dead end for areas other than the ones already examined.
I have an almost opposite problem. I spent years learning alot of ML stuff and worked at a job doing this kind of work for a couple years or so. I think the issue was that the data we had at the organization and the internal politics seemed to make it difficult to use for ML in a way that mattered to the business. I grew frustrated with having spent alot of time learning things that were exciting then realizing it didn't really matter if some manager can just say "we're doing it this other way that makes sense to me." (Not based on data, but gut feelings)<p>I'm not sure what to do with that. Probably ML works best in organizations and situations that are on board for using ML to make decisions for the business. Here's the other thing -- finding a business where ML is core to its decision making that will hire a person with no formal ML related education may be difficult. Perhaps I'm wrong about that and have just given up on ML after my frustrating experience.<p>Now I'm building data systems that the business uses on a daily basis to get things done. I feel alot better doing that than ML stuff, even though I loved playing with data and ML. I guess I've given up on ML for now, maybe I'll find my way back to it again.
Even I recently started with ML/DL but my approach is more theoretical way. I started with Andrew's course, but alongside doing Python Machine Learning textbook,while testing my self on Kaggle. I hope to build some interesting system soon. The only thing I am worried about is getting a full time job, which I think always require someone with 2+ year experience.
Admirable intentions by the author but I hope (s)he changes his font/formatting style.<p>The current font with dense paragraphs makes it hard for me to read without a headache, sparser sentences (either via bullet pointed lists or illustrative images) are much easier for me to parse.
@muratbuffalo Your graph has left the building. <a href="http://imgur.com/a/kKkjC" rel="nofollow">http://imgur.com/a/kKkjC</a>
Unfortunately the author begins by citing the fraud Taleb. After that I have to doubly examine everything he writes for signs of subtle nonsense, and its just necessary to close the tab.