A deep learning convolutional neural network model is used to explore the possibilities of estimating tropical cyclone (TC) intensity from satellite images in the 37- and 85–92-GHz bands. The model, called "DeepMicroNet," has unique properties such as a probabilistic output, the ability to operate from partial scans, and resiliency to imprecise TC center fixes. The 85–92-GHz band is the more influential data source in the model, with 37 GHz adding a marginal benefit. Training the model on global best track intensities produces model estimates precise enough to replicate known best track intensity biases when compared to aircraft reconnaissance observations. Model root-mean-square error (RMSE) is 14.3 kt (1 kt 0.5144 m s 1) compared to two years of independent best track records, but this improves to an RMSE of 10.6 kt when compared to the higher-standard aircraft reconnaissance-aided best track dataset, and to 9.6 kt compared to the reconnaissance-aided best track when using the higher-resolution TRMM TMI and Aqua AMSR-E microwave observations only. A shortage of training and independent testing data for category 5 TCs leaves the results at this intensity range inconclusive. Based on this initial study, the application of deep learning to TC intensity analysis holds tremendous promise for further development with more advanced methodologies and expanded training datasets. If you would like to learn more about this work check out the publication titled, "Using Deep Learning to Estimate Tropical Cyclone Intensity from Satellite Passive Microwave Imagery". If you would like to learn more about models for predicting tropical storms, checkout this presentation by NASA titled, "Tropical Cyclone Intensity Estimation Using Deep Convolutional Neural Networks".

Hewlett Packard Enterprise (HPE) today announced a container-based software solution, HPE ML Ops, to support the entire machine learning model lifecycle for on-premises, public cloud and hybrid cloud environments. The new solution introduces a DevOps-like process to standardize machine learning workflows and accelerate AI deployments from months to days. The new HPE ML Ops solution extends the capabilities of the BlueData EPIC container software platform, providing data science teams with on-demand access to containerized environments for distributed AI / ML and analytics. BlueData was acquired by HPE in November 2018 to bolster its AI, analytics, and container offerings, and complements HPE's Hybrid IT solutions and HPE Pointnext Services for enterprise AI deployments. Enterprise AI adoption has more than doubled in the last four years1, and organizations continue to invest significant time and resources in building machine learning and deep learning models for a wide range of AI use cases such as fraud detection, personalized medicine, and predictive customer analytics.

In today's article, we shall deep dive into video object tracking. Starting from the basics, we shall understand the need for object tracking, and then go through the challenges and algorithmic models to understand visual object tracking, finally, we shall cover the most popular deep learning based approaches to object tracking including MDNET, GOTURN, ROLO etc. This article expects that you are aware of object detection. Object tracking is the process of locating moving objects over time in videos. One can simply ask, why can't we use object detection in each frame in the whole video and we can track the object.

We've seen people turn neural networks to almost everything from drafting pickup lines to a new Harry Potter chapter, but it turns out classic text adventure games may be one of the best fits for AI yet. This latest glimpse into what artificial intelligence can do was created by a neuroscience student named Nathan. Nathan trained GPT-2, a neural net designed to create predictive text, on classic PC text adventure games. Inspired by the Mind Game in Ender's Game, his goal was to create a game that would react to the player. Since he uploaded the resulting game to a Google Colab notebook, people like research scientist Janelle Shane have had fun seeing what a text adventure created by an AI looks like.

One morning a few weeks ago Stephen Foot, a warehouseman from Enfield, woke up in a London hospital to discover the unlikely harbinger of a coming medical revolution. This Ghost of Healthcare to Come took the form of a nephrologist at the end of his bed. "That was the last thing I was expecting," he tells me. "Somebody from the renal department to come and say, 'Oh, by the way, there's something going on that has sparked an alert on your kidney.'" Foot had entered hospital because of his foot.

This post expands on the NAACL 2019 tutorial on Transfer Learning in NLP. The tutorial was organized by Matthew Peters, Swabha Swayamdipta, Thomas Wolf, and me. In this post, I highlight key insights and takeaways and provide updates based on recent work. The slides, a Colaboratory notebook, and code of the tutorial are available online. For an overview of what transfer learning is, have a look at this blog post. Transfer learning is a means to extract knowledge from a source setting and apply it to a different target setting. In the span of little more than a year, transfer learning in the form of pretrained language models has become ubiquitous in NLP and has contributed to the state of the art on a wide range of tasks.

A fun pastime for armchair philosophers of technology is whether the entire field of artificial intelligence, so riven with hype at the moment, will any day now experience a crushing fall-off in enthusiasm and a consequent collapse in funding. It's the notion of an "AI winter," and it has hit the field a couple of times in the past forty years, right after big breakthroughs. The answer is No, there won't be an AI winter. It's different for a simple reason: artificial intelligence, in its latest incarnation, called deep learning, has become "industrialized." For the first time ever, AI is part of how companies work.

I've been learning machine learning for the past two years now, these books have all been instrumental throughout. The Hundred-Page Machine Learning Book (buy) - https://bit.ly/100pagemlbook The Deep Learning Book (buy) - https://amzn.to/2YIsGok The Hundred-Page Machine Learning Book Review - https://youtu.be/btLxTTkSZuY Get email updates on my work - https://bit.ly/mrdbourkenewsletter

This post expands on the NAACL 2019 tutorial on Transfer Learning in NLP. The tutorial was organized by Matthew Peters, Swabha Swayamdipta, Thomas Wolf, and me. In this post, I highlight key insights and takeaways and provide updates based on recent work. The slides, a Colaboratory notebook, and code of the tutorial are available online. For an overview of what transfer learning is, have a look at this blog post. In the span of little more than a year, transfer learning in the form of pretrained language models has become ubiquitous in NLP and has contributed to the state of the art on a wide range of tasks.

Researchers have harnessed the power of artificial intelligence to decode x-ray images of the Ghent Altarpiece, the 15th-century masterpiece by brothers Hubert van Eyck and Jan van Eyck at the St. Bavo Cathedral in Belgium. Being able to read the x-rays can help identify damage to the painting by showing areas where varnish or overpainting hides cracks, paint loss, or other structural issues. The scans can also teach researchers about the artists' working methods, revealing the physical structure of the canvas or panel and its supports, as well as the different layers of paint used in its creation. But because the Ghent Altarpiece's panels are double sided, it has been difficult to parse the x-ray images. A newly developed algorithm has allowed scientists to deconstruct the data to create two distinct images.