"The field of Machine Learning seeks to answer these questions: How can we build computer systems that automatically improve with experience, and what are the fundamental laws that govern all learning processes?"
– from The Discipline of Machine Learning by Tom Mitchell. CMU-ML-06-108, 2006.
Deep learning is a sub-field of machine learning and an aspect of artificial intelligence. To understand this more easily, understand that it is meant to emulate the learning approach that humans use to acquire certain types of knowledge. This is somewhat different from machine learning, often people get confused in this and machine learning. Deep learning uses a sequencing algorithm while machine learning uses a linear algorithm. To understand this more accurately, understand this example that if a child is identified with a flower, then he will ask again and again, is this flower?
I want to talk about a misconception on the difference between inference and prediction. For a well run analytically oriented business, there may not be as many reasons to prefer inference over prediction one may have heard. A common refrain is: data scientists are in error in centering so much on prediction, a mistake no true Scotsman statistician would make. I've actually come to question this and more and more. Mere differences in practice between two fields doesn't immediately imply either field is inferior or in error.
In a survey conducted by Gurugram-based BML Munjal University (School of Law) in July 2020, it was found that about 42% of lawyers believed that in the next 3 to 5 years as much as 20% of regular, day-to-day legal works could be performed with technologies such as artificial intelligence. The survey also found that about 94% of law practitioners favoured research and analytics as to the most desirable skills in young lawyers. Earlier this year, Chief Justice of India SA Bobde, in no uncertain terms, underlined that the Indian judiciary must equip itself with incorporating artificial intelligence in its system, especially in dealing with document management and cases of repetitive nature. With more industries and professional sectors embracing AI and data analytics, the legal industry, albeit in a limited way, is no exception. According to the 2020 report of the National Judicial Data Grid, over the last decade, 3.7 million cases were pending across various courts in India, including high courts, district and taluka courts.
Using those primitives, DeepMind generated a dataset known as Procedurally Generated Matrices(PGM) that consists of triplets [progression, shape, color]. The relationship between the attributes in a triplet represent an abstract challenge. For instance, if the first attribute is progression, the values of the other two attributes must along rows or columns in the matrix. In order to show signs of abstract reasoning using PGM, a neural network must be able to explicitly compute relatioships between different matrix images and evaluate the viability of each potential answer in parallel. To address this challenge, the DeepMind team created a new neural network architecture called Wild Relation Network(WReN) in recognition of John Rave's wife Mary Wild who was also a contributor to the original IQ Test. In the WReN architecture, a convolutional neural network(CNN) processes each context panel and an individual answer choice panel independently to produce 9 vector embeddings. This set of embeddings is then passed to an recurrent network, whose output is a single sigmoid unit encoding the "score" for the associated answer choice panel.
For the visualization of features, the authors use deconvolutional networks (deconvnet). Think of deconvnet as decoder part of the autoencoders. It does the reverse of a normal convolutional network, it uses unpooling and filters to recover the pixels from the features. The only confusing part in this network is how it is undoing the pooling because when any pooling is done, only one value remains out of N² values given NxN filter was used. That whole data cannot be recovered but the max value is still there but it is no use if we don't know where it is located in the output of the convolutional layer.
A good example of solving for the right problems can be seen in Formula One World Championship Ltd. The motorsport company was looking for new ways to deliver race metrics that could change the way fans and teams experience racing, but had more than 65 years of historical race data to sift through. After aligning their technical and domain experts to determine what type of untapped data had the most potential to deliver value for its teams and fans, Formula 1 data scientists then used Amazon SageMaker to train deep learning models on this historical data to extract critical performance statistics, make race predictions and relay engaging insights to their fans into the split-second decisions and strategies adopted by teams and drivers.
Our initial attempts at representing wave functions with neural networks were met with frustration when we couldn't reach the accuracy of even the standard Hartree–Fock method of quantum chemistry. Not even on the smallest molecules, where such a calculation takes only a few seconds on a modern computer. This eventually motivated us to build the Hartree–Fock baseline and other components enforcing the correct physics of wavefunctions into our architecture, which we dubbed PauliNet--a neural network that obeys the Pauli exclusion principle.2 We were then quite surprised in September 2019 when we found out that researchers at DeepMind, who pursued the same idea in parallel, were able to reach impressive accuracy without building any physics into their architecture, called FermiNet, although at the cost of using much larger networks and hence requiring more computational resources.3
We aim to improve the World by using data and AI. Our Machine Learning Engineers are passionate about efficiently running cutting-edge AI models on a variety of hardware platforms and architectures. You will work closely with Researchers and Software Engineers, making AI prototypes become production-ready software and applying state-of-the-art techniques to optimize models for deployment while maintaining accuracy. It's a plus if you have: I will tell you why! Because we cultivate intelligence and learning and help people grow beyond their potential. This is your chance to build your career in a growing data driven industry.