Brains are quite simply the most amazing things. Do you want to know what's more fascinating to me? How we're able to adapt and learn completely new skills and form these new neural pathways. I have a little brother who's 6 years old and I've seen him grow up from a crying little helpless baby to a small human. He learned how to crawl, then to walk, run, how to form words, he learned to understand grammar, he learned to do basic math. I still remember the day that my parents brought him home.

One of the most exciting areas of deep learning is computer vision. Through recent advances in convolutional neural nets we have been able to create self driving cars, facial detection systems and automated medical imagery analysis that out performs specialists just to name a few. In this article I will show you the fundamentals of convolutional neural nets and how you can create one yourself to classify hand written digits. Unlike many fields of deep learning which are hyped to the public to seem like they are replications of biological functions in the human brain, convolutional neural nets come very close. Back in 1959, David Hubel and Torsten Wiesel conducted expirements on cats and monkeys which gave important revelations of how the visual cortex functions. What they found was that many neurons have a small local receptive which only react to small finite areas of the total visual field.

Many companies want to ride on the wave of machine learning and AI and are looking for ways to develop such systems into their business. The technology of machine learning, artificial intelligence, and deep learning specifically are relatively new, and the number of experts in this domain is limited. The main mistake that some of these companies are doing is to start with the technology and not with the business needs. They are hiring a couple of data scientists and give them access to the databases, and ask them to build something interesting from the data. It is true that you can find some interesting anecdotes in the data, but for a successful system, the process should be different.

I took a Deep Learning course through The Bradfield School of Computer Science in June. This series is a journal about what I learned in class, and what I've learned since. This is the first article in this series, and is is about the recommended preparation for the Deep Learning course and what we learned in the first class. Although normally the "prework" comes before the introduction, I'm going to give the 30,000 foot view of the fields of artificial intelligence, machine learning, and deep learning at the top. I have found that this context can really help us understand why the prerequisites seem so broad, and help us study just the essentials. Besides, the history and landscape of artificial intelligence is interesting, so lets dive in!

The project is about predicting coronary heart disease by using three different ML algorithms. And to know which is the best approach. There are roughly two controls per case of CHD. Many of the CHD positive men have undergone blood pressure reduction treatment and other programs to reduce their risk factors after their occurrence of CHD. In some cases the measurements were made after these treatments.

Once I finished converting all of the MP3 files into WAV files, I had to figure out how to load in the WAV data. Putting the data into a format that a neural network can work with, to me, was one of the hardest parts. This project took a lot of trial and error to get working correctly, but was pretty fun to figure out. To help me process the WAV files, I used TensorFlow's audio_ops library. I opted to use audio_ops to decode the WAV files into an array of samples that could then be processed and batched.

The history of science and technology is often delineated by paradigm shifts. A paradigm shift is a fundamental change in how we view the world and our relationship to it. The big paradigm shifts are sometimes even referred to as an "age" or a "revolution". The Space Age is a perfect example. The middle of the 20th Century saw not only an incredible increase in public awareness of space and space travel, but many of the industrial and technical advances that we now take for granted were byproducts of the Space Age.

This computational prowess of TPUs was possible mainly because of their three decisive features. One, TPUs eliminated unneeded accuracy while performing training and inference. Three, TPUs assumed a minimal and deterministic design where all unnecessary functions such as caching and branch prediction were removed. Such optimized TPUs are deployed on TPU pods, supercomputers specifically developed for machine learning. In order to ensure high performance of Cloud TPUs -- TPUs that we access through GCP -- a typical Cloud TPUs work with the architecture on the image.

A recent OpenAI report showed that "the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.5 month-doubling time", this is a 300.000x increase since 2012. These consequences can proof dire for smaller firms and researchers, limiting their ability to create competitive models without significant funding. And even with funding, they might be blacklisted from resources if they're considered competition by the providers. But big corporations will feel the costs as well considering both the growth rate of resources and the growth rate of their AI efforts multiplied. I spoke to a few Chief Data Officers of Fortune 500 firms over the past months, and while they don't consider it an issue yet, even they have to agree that they can invest their money in better ways than in bought-in HPC resources.

I haven't attended any formal education in probability & statistics, whatever I have learnt in bits and pieces till now is through working on data science problems. When I look at the literature available on probability & statistics, I find it too theoretical and generalized. I have felt that there should be some literature on probability & statistics specifically focused on data science. Recently couple of books have been written like'Practical Statistics for Data Scientists: 50 Essential Concepts' by Peter Bruce/Andrew Bruce, which are good and cover some of the context but I want to cover everything about probability & statistics from basics to statistical learning. I would like to mention that my focus in these posts would be to give intuition on every topic and how it relates to data science rather going deep into mathematical formulas.