If you've had anything to do with deep learning recently, you've heard of them: adversarial examples. Adversarial examples are one way of showing the limitations of neural networks when someone asks "is this how human vision works"?. In a nutshell, it is possible to change a few carefully chosen pixels in a picture of a panda, such that a network that was trained to distinguish pandas from cats will classify the picture of the panda as a picture of a cat. Now, note how I emphasized the word picture above. Because that is what we give to the network as input: a picture, a matrix of pixels.

UC San Francisco is upping its research into advanced computing in healthcare, launching an artificial intelligence center specifically to advance its use in medical imaging. The Center for Intelligent Imaging will develop and apply artificial intelligence in the quest to find new ways to use radiology to look inside the body and to evaluate health and disease. UCSF investigators in the center will work with Santa Clara, Calif-based NVIDIA, which develops AI products to support infrastructure and tools. The collaboration will aim to create new ways to enable the translation of AI into clinical practice. "Artificial intelligence represents the next frontier for diagnostic medicine," says Christopher Hess, MD, chair of UCSF's Department of Radiology and Biomedical Imaging.

This post is not meant for seasoned software engineers. This is geared towards data scientists and machine learning (ML) practitioners, who like me, do not come from a software engineering background. We use Python a lot for our work. It is on the way to becoming the fastest growing major language for modern data-driven analytics and artificial intelligence (AI) apps. However, it is also used for simple scripting purpose, to automate stuff, to test a hypothesis, create interactive plots for brainstorming, to control lab instruments, etc.

This is a curated list of tutorials, projects, libraries, videos, papers, books and anything related to the incredible PyTorch. Feel free to make a pull request to contribute to this list. Do feel free to contribute! You can raise an issue or submit a pull request, whichever is more convenient for you. The guideline is simple: just follow the format of the previous bullet point.

"One of the most exciting things about deep learning reconstruction is how it redefines the usual negotiation between exam time and image quality. This could lead to significant downstream value for imaging operations and for patient experience," said Christopher Hess, MD, Chair of the Department of Radiology and Biomedical Imaging at UCSF. SubtleMR delivers a significant improvement in the quality of noisy images, which is particularly beneficial for patients who have difficulty holding still for long periods of time. Artifact-ridden images and the need for re-scans are a challenge for both patients and physicians. SubtleMR integrates seamlessly into the radiology workflow, and it is compatible with any brand of MRI scanner and PACS.

The world has witnessed significant advancements in human-computer dialogue. Today, conversational interfaces are slowly taking the place of rigid GUI dialogue boxes and web forms. The evident evolution of UI design is all about leveraging artificial intelligence to enable end-users to get answers and perform routine tasks quickly without strain. However, what's the key to designing and building AI-powered and user-friendly chat interfaces? Chatbots are programs that facilitate text-based conversations between computers and people in a natural language.

In the fall of 2017, Sam Bowman, a computational linguist at New York University, figured that computers still weren't very good at understanding the written word. Sure, they had become decent at simulating that understanding in certain narrow domains, like automatic translation or sentiment analysis (for example, determining if a sentence sounds "mean or nice," he said). But Bowman wanted measurable evidence of the genuine article: bona fide, human-style reading comprehension in English. So he came up with a test. In an April 2018 paper coauthored with collaborators from the University of Washington and DeepMind, the Google-owned artificial intelligence company, Bowman introduced a battery of nine reading-comprehension tasks for computers called GLUE (General Language Understanding Evaluation). The test was designed as "a fairly representative sample of what the research community thought were interesting challenges," said Bowman, but also "pretty straightforward for humans."

In this week's Friday Faves, we have Tensorflow 2 dropping and a beautiful bonus, next level physics-based ML, and a problem with a Harvard deep learning paper. Tensorflow 2.0 dropped this week and it has Eager Execution (read "normal behaviour") per default and the Keras API per default. If you're familiar with PyTorch, you'll wonder "that's news?" but you can now use one of three, which for PyTorch users will be another "that's news?" Depending on how reproducible and complicated your model gets, you'll need to make that choice. I have personally yet to use Subclassing, but I hear good things.

"exploring the humanizing of AI by building a digital brain which can be used as a platform for autonomously animating hyper-realistic digital humans" "I think what will be increasingly important in the digital human space is ethics, as they relate both to the digital human and to the real-life people who may be impacted. From a digital human perspective, companies are essentially birthing entities which, in many cases, are expected to form meaningful connections and relationships with people. So how organizations treat these digital humans--including any decision to dispose of them if they are no longer deemed needed--will increasingly become important. On the flipside, entertainment organizations that are using digital humans run the risk of causing concern of replacing real humans […] and it will be important to clarify how and why digital humans are being used in lieu of the'real' thing." Excerpts from this article: The Virtual Beings Are Arriving Efficient deployment of deep learning models requires specialized neural network architectures to best fit different hardware platforms and efficiency constraints (defined as deployment scenarios).

This paper proposes a deep neural network approach for predicting multiphase flow in heterogeneous domains with high computational efficiency. The deep neural network model is able to handle permeability heterogeneity in high dimensional systems, and can learn the interplay of viscous, gravity, and capillary forces from small data sets. Using the example of carbon dioxide (CO2) storage, we demonstrate that the model can generate highly accurate predictions of a CO2 saturation distribution given a permeability field, injection duration, injection rate, and injection location. The trained neural network model has an excellent ability to interpolate and to a limited extent, the ability to extrapolate beyond the training data ranges. To improve the prediction accuracy when the neural network model needs to extrapolate, we propose a transfer learning (fine-tuning) procedure that can quickly teach the neural network model new information without going through massive data collection and retraining. Based on this trained neural network model, a web-based tool is provided that allows users to perform CO2-water multiphase flow calculations online. With the tools provided in this paper, the deep neural network approach can provide a computationally efficient substitute for repetitive forward multiphase flow simulations, which can be adopted to the context of history matching and uncertainty quantification.