Since we originally proposed the need for a first-class language, compiler and ecosystem for machine learning (ML) - a view that is increasingly shared by many, there have been plenty of interesting developments in the field. Not only have the tradeoffs in existing systems, such as TensorFlow and PyTorch, not been resolved, but they are clearer than ever now that both frameworks contain distinct "static graph" and "eager execution" interfaces. Meanwhile, the idea of ML models fundamentally being differentiable algorithms – often called differentiable programming – has caught on.

Where current frameworks fall short, several exciting new projects have sprung up that dispense with graphs entirely, to bring differentiable programming to the mainstream. Myia, by the Theano team, differentiates and compiles a subset of Python to high-performance GPU code. Swift for TensorFlow extends Swift so that compatible functions can be compiled to TensorFlow graphs. And finally, the Flux ecosystem is extending Julia’s compiler with a number of ML-focused tools, including first-class gradients, just-in-time CUDA kernel compilation, automatic batching and support for new hardware such as TPUs.

This talk will demonstrate how Julia is increasingly becoming a natural language for machine learning, the kind of libraries and applications the Julia community is building, the contributions from India (there are many!), and our plans going forward.

Machine learning and deep learning have been rapidly adopted in various spheres of medicine such as discovery of drug, disease diagnosis, Genomics, medical imaging and bioinformatics for translating biomedical data into improved human healthcare. Machine learning/deep learning based healthcare applications assist physicians to make faster, cheaper and more accurate diagnosis.

We have successfully developed three deep learning based healthcare applications and are currently working on two more healthcare related projects. In this workshop, we will discuss one healthcare application titled "Deep Learning based Craniofacial Distance Measurement for Facial Reconstructive Surgery" which is developed by us using TensorFlow. Craniofacial distances play important role in providing information related to facial structure. They include measurements of head and face which are to be measured from image. They are used in facial reconstructive surgeries such as cephalometry, treatment planning of various malocclusions, craniofacial anomalies, facial contouring, facial rejuvenation and different forehead surgeries in which reliable and accurate data are very important and cannot be compromised.

Our discussion on healthcare application will include precise problem statement, the major steps involved in the solution (deep learning based face detection & facial landmarking and craniofacial distance measurement), data set, experimental analysis and challenges faced & overcame to achieve this success. Subsequently, we will provide hands-on exposure to implement this healthcare solution using TensorFlow. Finally, we will briefly discuss the possible extensions of our work and the future scope of research in healthcare sector.

Banks and financial institutes in India over the last few years have increasingly faced defaults by corporates. In fact, NBFC stocks have suffered huge losses in recent times. It has triggered a contagion which spilled over to other financial stocks too and adversely affected benchmark indices resulting in short term bearishness. This makes it imperative to investigate ways to prevent rather than cure such situations. However, the banks face a twin-faced challenge in terms of identifying the probable wilful defaulters from the rest and moral hazard among the bank employees who are many a time found to be acting on behest of promoters of defaulting firms. The first challenge is aggravated by the fact that due diligence of firms before the extension of loan is a time-consuming process and the second challenge hints at the need for placement of automated safeguards to reduce mal-practises originating out of the human behaviour. To address these challenges, the automation of loan sanctioning process is a possible solution. Hence, we identified important firmographic variables viz. financial ratios and their historic patterns by looking at the firms listed as dirty dozen by Reserve Bank of India. Next, we used k-means clustering to segment these firms and label them into various categories viz. normal, distressed defaulter and wilful defaulter. Besides, we utilized text and sentiment analysis to analyze the annual reports of all BSE and NSE listed firms over the last 10 years. From this, we identified word tags which resonate well with the occurrence of default and are indicators of financial performance of these firms. A rigorous analysis of these word tags (anagrams, bi-grams and co-located words) over a period of 10 years for more than 100 firms indicate the existence of a relation between frequency of word tags and firm default. Lift estimation of firmographic financial ratios namely Altman Z score and frequency of word tags for the first time uncovers the importance of text analysis in predicting financial performance of firms and their default. Our investigation also reveals the possibility of using neural networks as a predictor of firm default. Interestingly, the neural network developed by us utilizes the power of open source machine learning libraries and throws open possibilities of deploying such a neural network model by banks with a small one-time investment. In short, our work demonstrates the ability of machine learning in addressing challenges related to prevention of wilful default. We envisage that the implementation of neural network based prediction models and text analysis of firm-specific financial reports could help financial industry save millions in recovery and restructuring of loans.