anantzoid

Thanks for putting so much time and effort into this. This is definitely not "Yet-another-intro-to-ML".

Which particular troubling event related to India are you referring to?

Interesting. What is your training objective in deciding which view of the room would be the most appealing? Also, are you looking into generative models for creating new views from different angles based on existing views?

Unrelated: gosh, I like the content of the video presentation but it would be nice if Musk was a slightly better presenter.

Same goes for the audience. I heard one shouting "Save us Elon!". Where do they get these people from?

Maybe it doesn't teach anything new, but it does act as a refresher and makes you go back to Deep Work. I had almost completely forgotten about it and my work schedule was full of tab switching and short breaks. After going through the book, I started using Toggl and minding my time.

But don't they earn through ads? Like other news websites.

The link is in the description of the projects.

This is awesome. Almost everytime I've to launch an instance for a new app or something, I end up googling "aws ec2 instances", "ec2 pricing" etc.

Exactly. If you're a ML person, you must be working with Linux in most cases. And in such case, you need to be familiar with the types of permissions, cause that's relevant even during the installation of various libraries, doing ssh etc.

Spot instances cost way cheaper. The only downside is you need to create an AMI everytime before termination. But, also, AWS g2 has NVIDIA Grid K50 with 4GB memory, so it's not very good with performance.

Unfortunately, it only covers about Musk till his Paypal days. From Chapter 5 about SpaceX, he just has a guest appearance in the story, which mostly goes to describe the factories, the deals etc. I really expected the book to hold what Elon thought during Tesla's low times. His motivation that kept him going in SpaceX even after subsequent crashes etc.

I used to do boxing earlier in college, and used to hit the gym religiously till last year, when my elbow fractured and got implants to hold it together. After that I wasn't able to do much activity, even if I wanted, apart from running. Even pushups carry a risk of screwing up the implants in my elbow.

What kind of physical activity do you think can be done in this type of scenario?

The corresponding paper linked in the blog post explains the recommendation system behind Google App Store. The recommendations generated from this model led to a significant increase in app downloads.

"One main resource" as in, it goes through all the underlying math required in details etc. It's usually assumed that people entering into DL have some experience with Machine Learning. Of course, for someone staring with ML, CS229 is the first thing she should pick up.

Greg Brockman (Founder of Open AI) has written this amazing answer:

If you want to read one main resource... the Goodfellow, Bengio, Courville book (available for free from http://www.deeplearningbook.org/) is an extremely comprehensive survey of the field. It contains essentially all the concepts and intuition needed for deep learning engineering (except reinforcement learning).

If you'd like to take courses... Pieter Abbeel and Wojciech Zaremba suggest the following course sequence:

- Linear Algebra — Stephen Boyd’s EE263 (Stanford) - Neural Networks for Machine Learning — Geoff Hinton (Coursera) - Neural Nets — Andrej Karpathy’s CS231N (Stanford) - Advanced Robotics (the MDP / optimal control lectures) — Pieter Abbeel’s CS287 (Berkeley) - Deep RL — John Schulman’s CS294-112 (Berkeley)

(Pieter also recommends the Cover & Thomas information theory and Nocedal & Wright nonlinear optimization books).

If you'd like to get your hands dirty... Ilya Sutskever recommends implementing simple MNIST classifiers, small convnets, reimplementing char-rnn, and then playing with a big convnet. Personally, I started out by picking Kaggle competitions (especially the "Knowledge" ones) and using those as a source of problems. Implementing agents for OpenAI Gym (or algorithms for the set of research problems we’ll be releasing soon) could also be a good starting place.

Quora link: https://www.quora.com/What-are-the-best-ways-to-pick-up-Deep...

I had the opportunity to study Coursera's ML course a couple of years back when I was in college and developed a deep passion for the area. I was out of touch with ML since 1.5 years and now coming back to it seems overwhelming. I mean there is so much more to learn. The gap between classic ML and Deep Learning is noticeably huge. This is due to the rapid development in the recent years. You won't get things like gradient clipping, learning decay, dropouts etc. in the coursera course. Moreover, new papers are released every other day and one needs to devote time to stay updated.

And when I think about people who are not familiar with even Machine Learning, then really need to buckle up and spend serious time to catch-up with the technology that's making history today.

But now is really a good time to start. There are only a bunch of people in the whole wide world who are masters of DL and anyone with skills in it is in high demand. And it's not just about a job, "it is really cool" to play with it. I really feel I'm doing something heavy.

In fact, the recent massive success of Deep Neural Nets have led to the terms 'Artificial Intelligence', 'Machine Learning' and 'Deep Learning' being used interchangeably. This was not the case till early 2015. In order to inform the masses about the breakthroughs, the media started generalising DNNs as AI, and also because this was the only AI technique to show such results.

I also like https://github.com/svenstaro/flamejam/ as a good example of Flask architecture. It's simple and maintainable. I wrote a 4k+ loc app using a similar pattern and it still remains quite easy to handle.

Wow! I didn't realize it was satirical and thought is the author a con or crazy. Then I headed here and the news broke out for me. I'm pretty sure majority of people who only read about ML in press will take it seriously.

If the government succeeds in this case, it'll be George Orwell's 1984 everywhere. A constant monitoring will be done on everyone irrespective of who they are. The terrorists will move on to another stream of communication (I think ISIS already has their own app), and only the innocent citizens will be left to be monitored by the FBI.

You've a choice of 25 frameworks, libraries, tools that change every day and break between versions.

And this is what the author has said too, and then presented a list of tools for different purposes to one doesn't fall into analysis-paralysis.

Since past few months, JS community and settling down and tools are getting stable and long lasting. Surely, new ones are being developed everyday, but a standard is being set with React-Redux-Webpack family.

Maybe a new generation of JS tools will come up when Web Assembly becomes mainstream, but until then, I think React is here to stay.

Google Now takes the user's voice into account during setup and usually responds only to the user's voice. Such a system should have been implemented in Echo too.

Also, it helps in taking the community point of view. Right now, if a newbie submits a PR, one of the project maintainer might just diss him and claim his PR to be irrelevant. But if there are already some 10 likes, the latter might give a second thought and might look at it from a different perspective.

It's like another intelligent species opening up a new way of looking at the world.

And this is just the beginning with AlphaGo. As we keep on training Deep Learning systems for other domains, we'll realise how differently they approach problems and solve them. It'll, in turn, help us in adapting these different perspectives and applying them to solve other problems as well.

The point that's not stressed enough is the massive amounts of good data that is needed to fuel these kind of systems. Data collection, cleaning, aggregation and other processes itself are humungous tasks.

I passed 3 interviews with 6 interviewers for Booking (they even flew me to Amsterdam for that). 1 of them didn't seem to like me, even before I answered his questions. The rest were very impressed (as stated in the feedback). Got rejected.

I tried using it for one of my projects, but the feature support is very little, and I had to actually manually draw the nodes. Reverted back to using D3.js, which, though having a high learning curve, gracefully solved my problem.

If it's not very different from DejaVu Sans mono, why not use the latter itself in the first place?

Other apps getting slow is also not a very good thing!

Let's hope they use this to stabilize their systems and make it more reliable. Have been extensively using their service, and there are times when the SMS doesn't get delivered.