In my last article, I wrote a general overview of Big Data Analytics in Healthcare. Researchers at IBM estimate that medical images currently account for at least 90 percent of all medical data, making it the largest data source in the healthcare industry. This becomes an overwhelming amount on a human scale, when you consider that radiologists in some hospital emergency rooms are presented with thousands of images daily, most of which are not analyzed properly. Due to the large facets of healthcare processes, it is not uncommon to create datasets with over 10,000 or more features even after dimensionality reduction. Deep learning has shown that being able to train large models on vasts amount of data can drastically improve model performance.

In the last decade, artificial intelligence ("AI") applications have exploded across various research sectors, including computer vision, communications and medicine. Now, the rapidly developing technology is making its mark in weather prediction. The fields of atmospheric science and satellite meteorology are ideally suited for the task, offering a rich training ground capable of feeding an AI system's endless appetite for data. Anthony Wimmers is a scientist with the University of Wisconsin–Madison Cooperative Institute for Meteorological Satellite Studies (CIMSS) who has been working with AI systems for the last three years. His latest research investigates how an AI model can help improve short-term forecasting (or "nowcasting") of hurricanes. Known as DeepMicroNet, the model uses deep learning, a type of neural network arranged in "deep" interacting layers that finds patterns within a dataset.

Recurrent neural networks are powerful sequence learners. They are able to incorporate context information in a flexible way, and are robust to localised distortions of the input data. These properties make them well suited to sequence labelling, where input sequences are transcribed with streams of labels. The aim of this thesis is to advance the state-of-the-art in supervised sequence labelling with recurrent networks.

Insilico Medicine has achieved a world first by successfully designing, synthesizing, and validating a new drug from the ground up and taking just 46 days to do so. It achieved this impressive feat using AI. This is the first time that AI has been used to successfully create a new drug, and it took record time compared to traditional methods. The company used Generative Adversarial Networks (GANs) back in 2016 to design new kinds of molecules and have further developed the system, combining it with reinforcement learning (RL) in order to develop new drugs and biomarkers. The new drug works by blocking the activity of the DDR1 kinase, which is implicated in fibrosis.

Microsoft bets on deep learning to enhance the Microsoft Defender Advanced Threat Protection (ATP) malicious PowerShell detection feature using a new technique originally developed for natural language processing (NLP). The new deep learning model is "now adopted and applied to expand our coverage of detecting malicious PowerShell scripts, which continue to be a critical attack vector," says Microsoft. Microsoft's deep learning model used for malicious PowerShell script detection "combines several deep learning building blocks such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN)." The company adopted the best performing model designed for NLP and trained on collections of PowerShell scripts the Microsoft Defender ATP platform observed via the Antimalware Scan Interface (AMSI). After its first deployment on Microsoft Defender ATP, this deep learning model specifically trained for spotting malicious scripts was able to find malicious PowerShell behavior that bypassed other Microsoft Defender ATP monitoring features.

Machine learning enables us to build systems that can predict the world around us: like what movies we'd like to watch, how much traffic we'll experience on our morning commute, or what words we'll type next in our emails. There are many types of models and tasks. Face detection models transform raw image pixels into high level signals (like the presence and position of eyes, noses, and ears) and then use those signals to locate all faces in an image. Time series models can use sensor measurements to extract long-term trends and seasonal patterns in order to predict future observations. Text prediction models extract information about the meaning of past sentences, grammaticality, and emotions in the text in order to predict the next word or phrase that you'll type.

Edge computing devices are becoming the logical destination to run deep learning models. While the public cloud is the preferred environment for training, it is the edge that runs the models for inferencing. Since most of the edge devices have constraints in the form of available CPU and GPU resources, there are purpose-built AI chips designed to accelerate the inferencing. These AI accelerators complement the CPU by speeding up the calculations involved in inferencing. They are designed to optimize the forward propagation of neural networks deployed on the edge.

The primary professional hat I wear is as a data science consultant working with machine learning in a variety of problem domains. Due to my academic past in computer science and applied statistics, my development environment of choice today is typically R. Lately however, Python is taking the lead position for working with deep learning workloads, so that's why I took special notice of this ODSC West 2018 talk "Deep Learning in R with Keras," presented by Gabriela de Queiroz, Senior Developer Advocate at IBM (Center for Open Source Data & AI). Gabriela is also Founder of the R-Ladies group. With Keras on top of R, I can get a little more mileage out of my R experience. For those of you still making the transition to deep learning, Keras is an open-source neural network library written in Python and capable of running on top of TensorFlow, Microsoft Cognitive Toolkit (CNTK), or Theano.

This notebook collection is inspired by the book Deep Learning with Python. To learn more about using Keras with TensorFlow, see the TensorFlow Keras Guide. Publisher's note: Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples. To learn about machine learning fundamentals and concepts, consider taking the Machine Learning Crash Course.