Almost every one of us was introduced to this field of automation, with jargons like Artificial Intelligence(AI), Machine Learning (ML), Deep Learning (DL), Data Science/Analytics, etc., which seemed like magic at first sight. The backbone of the course'Data Science' and those magical terms rests on these below topics: Note: The coursework I did in Machine Learning & Deep Learning was based on python, but there are alternatives like R, MATLAB, etc. but python is the most popular choice. Additionally, problem-solving or standard coding for questions is something students are familiar with throughout academia, but scripting the code in a refined, readable manner is very important when you are writing code for projects especially the ones in production. It's because when you are collaborating on a project, your team members need to be comfortable with your code at first sight. This helps them to improve your code and highly increases the efficiency of your project work.

Human interaction with machines has experienced a great leap forward in recent years, largely driven by artificial intelligence (AI). From smart homes to self-driving cars, AI has become a seamless part of our daily lives. Voice interactions play a key role in many of these technological advances, most notably in language translation. Here, AI enables instant translation across a number of mediums: text, voice, images and even street signs. The technology works by recognizing individual words, then leveraging similarities in how various languages express the relationships between those words.

Machine learning is taking medical diagnosis by storm. From eye disease, breast and other cancers, to more amorphous neurological disorders, AI is routinely matching physician performance, if not beating them outright. Yet how much can we take those results at face value? When it comes to life and death decisions, when can we put our full trust in enigmatic algorithms--"black boxes" that even their creators cannot fully explain or understand? The problem gets more complex as medical AI crosses multiple disciplines and developers, including both academic and industry powerhouses such as Google, Amazon, or Apple, with disparate incentives.

Researchers from all over the world contribute to this repository as a prelude to the peer review process for publication in traditional journals. The articles listed below represent a small fraction of all articles appearing on the preprint server. They are listed in no particular order with a link to each paper along with a brief overview. Links to GitHub repos are provided when available. Especially relevant articles are marked with a "thumbs up" icon.

After going through a lot of theoretical articles on recurrent layers, I just wanted to build my first LSTM model and train it on some texts! But the huge list of exposed parameters for the layer and the delicacies of layer structures were too complicated for me. This meant I had to spend a lot of time going through StackOverflow and API definitions to get a clearer picture. This article is an attempt to consolidate all of the notes which can accelerate the process of transition from theory to practice. The goal of this guide is to develop a practical understanding of using recurrent layers like RNN and LSTM rather than to provide theoretical understanding.

Uday Kamath has more than 20 years of experience architecting and building analytics-based commercial solutions. He currently works as the Chief Analytics Officer at Digital Reasoning, one of the leading companies in AI for NLP and Speech Recognition, heading the Applied Machine Learning research group. Most recently, Uday served as the Chief Data Scientist at BAE Systems Applied Intelligence, building machine learning products and solutions for the financial industry, focused on fraud, compliance, and cybersecurity. Uday has previously authored many books on machine learning such as Machine Learning: End-to-End guide for Java developers: Data Analysis, Machine Learning, and Neural Networks simplified and Mastering Java Machine Learning: A Java developer's guide to implementing machine learning and big data architectures. Uday has published many academic papers in different machine learning journals and conferences.

Artificial intelligence has arrived in our everyday lives--from search engines to self-driving cars. This has to do with the enormous computing power that has become available in recent years. But new results from AI research now show that simpler, smaller neural networks can be used to solve certain tasks even better, more efficiently, and more reliably than ever before. An international research team from TU Wien (Vienna), IST Austria and MIT (USA) has developed a new artificial intelligence system based on the brains of tiny animals, such as threadworms. This novel AI-system can control a vehicle with just a few artificial neurons.

The current practice in machine learning is traditionally model-centric, casting problems as optimization over model parameters, all the while assuming the data is either fixed, or subject to extrinsic and inevitable change. On one hand, this paradigm fails to capture important existing aspects of machine learning, such as the substantial data manipulation (\emph{e.g.}, augmentation) that goes into most state-of-the-art pipelines. On the other hand, this viewpoint is ill-suited to formalize novel data-centric problems, such as model-agnostic transfer learning or dataset synthesis. In this work, we view these and other problems through the lens of \textit{dataset optimization}, casting them as optimization over data-generating distributions. We approach this class of problems through Wasserstein gradient flows in probability space, and derive practical and efficient particle-based methods for a flexible but well-behaved class of objective functions. Through various experiments on synthetic and real datasets, we show that this framework provides a principled and effective approach to dataset shaping, transfer, and interpolation.

Large, multidimensional spatiotemporal datasets are omnipresent in modern science and engineering. An effective framework for handling such data are Gaussian process deep generative models (GP-DGMs), which employ GP priors over the latent variables of DGMs. Existing approaches for performing inference in GP-DGMs do not support sparse GP approximations based on inducing points, which are essential for the computational efficiency of GPs, nor do they handle missing data - a natural occurrence in many spatiotemporal datasets - in a principled manner. We address these shortcomings with the development of the sparse Gaussian process variational autoencoder (SGP-VAE), characterised by the use of partial inference networks for parameterising sparse GP approximations. Leveraging the benefits of amortised variational inference, the SGP-VAE enables inference in multi-output sparse GPs on previously unobserved data with no additional training. The SGP-VAE is evaluated in a variety of experiments where it outperforms alternative approaches including multi-output GPs and structured VAEs. Increasing amounts of large, multidimensional datasets that exhibit strong spatiotemporal dependencies are arising from a wealth of domains, including earth, social and environmental sciences (Atluri et al., 2018). For example, consider modelling daily atmospheric measurements taken by weather stations situated across the globe. Such data are (1) large in number; (2) subject to strong spatiotemporal dependencies; (3) multidimensional; and (4) non-Gaussian with complex dependencies across outputs.

Our interest is in scientific problems with the following characteristics: (1) Data are naturally represented as graphs; (2) The amount of data available is typically small; and (3) There is significant domain-knowledge, usually expressed in some symbolic form. These kinds of problems have been addressed effectively in the past by Inductive Logic Programming (ILP), by virtue of 2 important characteristics: (a) The use of a representation language that easily captures the relation encoded in graph-structured data, and (b) The inclusion of prior information encoded as domain-specific relations, that can alleviate problems of data scarcity, and construct new relations. Recent advances have seen the emergence of deep neural networks specifically developed for graph-structured data (Graph-based Neural Networks, or GNNs). While GNNs have been shown to be able to handle graph-structured data, less has been done to investigate the inclusion of domain-knowledge. Here we investigate this aspect of GNNs empirically by employing an operation we term "vertex-enrichment" and denote the corresponding GNNs as "VEGNNs". Using over 70 real-world datasets and substantial amounts of symbolic domain-knowledge, we examine the result of vertex-enrichment across 5 different variants of GNNs. Our results provide support for the following: (a) Inclusion of domain-knowledge by vertex-enrichment can significantly improve the performance of a GNN. That is, the performance VEGNNs is significantly better than GNNs across all GNN variants; (b) The inclusion of domain-specific relations constructed using ILP improves the performance of VEGNNs, across all GNN variants. Taken together, the results provide evidence that it is possible to incorporate symbolic domain knowledge into a GNN, and that ILP can play an important role in providing high-level relationships that are not easily discovered by a GNN.