About Me

I am a teacher and researcher working in the field of security and privacy. Find out more about me on the About page or see my research output on the Publications page.

Advertisements

Practical Deep Learning with Keras and Python (New Video Course)

I’ve just finished creating a new video course on Udemy about Practical Deep Learning with Keras and Python. It’s aimed at two types of people:

  1. Those who are just coming to machine learning and deep learning and want a soft (code-based introduction) as opposed to the mathematical treatment typically given to the subject.
  2. Those who have had ML/DL before but have trouble applying the concepts in code.

For the dedicated readers of my blog, I’m making it available at the minimum price of just $9.99. Please use the following coupon link to access it at this price.

https://www.udemy.com/practical-deep-learning-with-keras/?couponCode=RECLYBLOG

If you want to receive updates about content uploads, coupons and promotions, please subscribe to my mailing list here on mailchimp.

 

Deep Learning Experiments on Google’s GPU Machines for Free

Update: If you are interested in getting a running start to machine learning and deep learning, I have created a course that I’m offering to my dedicated readers for just $9.99. Practical Deep Learning with Keras and Python .

So you’ve been working on Machine Learning and Deep Learning and have realized that it’s a slow process that requires a lot of compute power. Power that is not very affordable. Fear not! We have a way of using a playground for running our experiments on Google’s GPU machines for free. In this little how-to, I will share a link with you that you can copy to your Google Drive and use it to run your own experiments.

BTW, if you would like to receive updates when I post similar content, please signup below:

Signup for promotions, course coupons and new content notifications through a short form here.

Colaboratory

First, sign in to an account that has access to Google Drive (this would typically be any Google/Gmail account). Then, click on this link over here that has my playground document and follow the instructions below to get your own private copy.Read More »

Machine Learning Crash Intro

Update: If you are interested in getting a running start to machine learning and deep learning, I have created a course that I’m offering to my dedicated readers for just $9.99. Practical Deep Learning with Keras and Python.

I gave a talk on Practical Machine Learning, which was well received. It covers the concepts from absolute scratch and covers all prerequisites. It also covers the theoretical foundations. Please go through the videos and let me know how I can improve them.

If you would like to receive updates when I post similar content, please signup below:

Signup for promotions, course coupons and new content notifications through a short form here.

Part 02 wasn’t recorded but you can start with 03 without it.

Deep Learning for Protein Function Prediction

Protein function prediction is taking information about a protein (such as its amino acid sequence, 2D and 3D structure etc.) and trying to predict which functions it will exhibit. This has implications in several areas of bioinformatics and affects how drugs are created and diseases are studied. This is typically an intensive task requiring inputs from biologists and computer experts alike and annotating newly found proteins requires empirical as well as computational results.

We, here at FAST NU, recently came up with a unique method (dubbed DeepSeq — since it’s based on Deep Learning and works on protein sequences!) for predicting functions of proteins using only the amino acid sequences. This is the information that is the first bit we get when a new protein is found and is thus readily available. (Other pieces require a lot more effort.)

We have successfully applied DeepSeq to predict protein function from sequences alone without requiring any input from domain experts. The paper isn’t peer reviewed yet but we have made the paper available as preprint and our full code on github so you can review it yourself.

We believe DeepSeq is going to be a breakthrough inshaallah in the field of bioinformatics and how function prediction is done. Let’s see if I can come up with an update about this in a year after the paper has been read a few times by domain experts and we have a detailed peer review.

DeepSeq

Machine Learning Video Lectures

Update: If you are interested in getting a running start to machine learning and deep learning, I have created a course that I’m offering to my dedicated readers for just $9.99. Practical Deep Learning with Keras and Python.

I taught an introductory Machine Learning course to BS students at FAST Peshawar in Fall 2015. The feedback was quite positive so I decided to offer another course to the MS/PhD students in the next semester. The mode of teaching was also a bit different: we tried doing the pen-tablet-augmented-multimedia-slides model. The semester is still in progress but we have the core of the basics done now.

The lectures are in Urdu so might be easier to follow for those who understand the language. I will be uploading the future videos as they come up inshaallah. You can see the first video below and follow the complete collection on Vimeo here: https://vimeo.com/album/3770825

Machine Learning – Lecture 01-A (Spring 2016) from recluze on Vimeo.

Machine Learning Self-Study Track

I started with Machine Learning a while back and had a slightly hard time getting help from the local community. The reason was mostly because the Machine Learning community in general is way behind the state-of-the-art in industry and research. This is true for almost all fields nowadays but with Machine Learning, the issues are more pronounced due to the recent fast-paced developments in the industry.

On the other hand, once you know what to study, things are much easier than many other fields such as security. Here I would outline the plan I followed to get to where I am (which isn’t too far ahead but still a little better than what most people know, IMHO).

So, here’s my guide for getting started with Machine Learning self-study.

  1. Start with Andrew Ng’s Coursera course — Machine Learning. That’s the advice almost everyone seems to give — and it’s a great advice. The Coursera course is completely basic and eases you in the field with little pre-reqs and not much depth. Be careful though: do not think after completing the course that you are an expert in Machine Learning. It misses quite a few areas and the skills needed to be above average. It does get you started with practicals so you are likely to think you’re already done after finishing the course.
  2. So, after you complete the courser in its entirety — including the assignments — I suggest you start with Prof. Nando de Freitas’ undergrad course.  This is a much more detailed course and would get you a very different view of ML than traditional outlines. Of course, you might have to brush up on your Probability, Calculus and Linear Algebra. You can’t really do anything without these three.
  3. For the above three, I suggest the following courses:
    1. Probability: Probability for Life Sciences by UCLA’s Math Department. You can find videos for this easily.
    2. Calculus: I strongly suggest you go with Virtual University Pakistan’s Calculus-I course by Dr. Faisal Shah Khan. It’s a great course but it’s in Urdu. If you don’t know Urdu, you can find your own series. Please let me know in the comments about great resources for this.
    3. Linear Algebra: Of course, this can only be done with Gilbert Strang’s Linear Algebra course from OCW.
  4. After that, you can start with the grad course and the second grad course by Prof. Nando de Freitas. Both have very detailed video lectures.

Of course, you also need to work with tools other than Matlab. I strongly suggest the python PyData stack. The full list would be:

  1. Python PyData full stack (plus go through their yearly videos as well)
  2. Theano
  3. Torch
  4. Keras

That’s what I have till now. I might add more when I know more inshaallah.