Biomolecular graph analysis has recently gained much attention in the emerging field of geometric deep learning. While numerous approaches aim to train classifiers that accurately predict molecular properties from graphs that encode their structure, an equally important task is to organize biomolecular graphs in ways that expose meaningful relations and variations between them. We propose a geometric scattering autoencoder (GSAE) network for learning such graph embeddings. Our embedding network first extracts rich graph features using the recently proposed geometric scattering transform. Then, it leverages a semi-supervised variational autoencoder to extract a low-dimensional embedding that retains the information in these features that enable prediction of molecular properties as well as characterize graphs. Our approach is based on the intuition that geometric scattering generates multi-resolution features with in-built invariance to deformations, but as they are unsupervised, these features may not be tuned for optimally capturing relevant domain-specific properties. We demonstrate the effectiveness of our approach to data exploration of RNA foldings. Like proteins, RNA molecules can fold to create low energy functional structures such as hairpins, but the landscape of possible folds and fold sequences are not well visualized by existing methods. We show that GSAE organizes RNA graphs both by structure and energy, accurately reflecting bistable RNA structures. Furthermore, it enables interpolation of embedded molecule sequences mimicking folding trajectories. Finally, using an auxiliary inverse-scattering model, we demonstrate our ability to generate synthetic RNA graphs along the trajectory thus providing hypothetical folding sequences for further analysis.

With the rapid growth and prevalence of social network applications (Apps) in recent years, understanding user engagement has become increasingly important, to provide useful insights for future App design and development. While several promising neural modeling approaches were recently pioneered for accurate user engagement prediction, their black-box designs are unfortunately limited in model explainability. In this paper, we study a novel problem of explainable user engagement prediction for social network Apps. First, we propose a flexible definition of user engagement for various business scenarios, based on future metric expectations. Next, we design an end-to-end neural framework, FATE, which incorporates three key factors that we identify to influence user engagement, namely friendships, user actions, and temporal dynamics to achieve explainable engagement predictions. FATE is based on a tensor-based graph neural network (GNN), LSTM and a mixture attention mechanism, which allows for (a) predictive explanations based on learned weights across different feature categories, (b) reduced network complexity, and (c) improved performance in both prediction accuracy and training/inference time. We conduct extensive experiments on two large-scale datasets from Snapchat, where FATE outperforms state-of-the-art approaches by ${\approx}10\%$ error and ${\approx}20\%$ runtime reduction. We also evaluate explanations from FATE, showing strong quantitative and qualitative performance.

The land cover classification has played an important role in remote sensing because it can intelligently identify things in one huge remote sensing image to reduce the work of humans. However, a lot of classification methods are designed based on the pixel feature or limited spatial feature of the remote sensing image, which limits the classification accuracy and universality of their methods. This paper proposed a novel method to take into the information of remote sensing image, i.e., geographic latitude-longitude information. In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image. Then, the features of the two neural networks are fused with another fully neural network to realize the classification of remote sensing images. Finally, two remote sensing images are used to verify the effectiveness of our method, including hyperspectral imaging (HSI) and polarimetric synthetic aperture radar (PolSAR) imagery. The result of the proposed method is superior to the traditional single-channel convolutional neural network.

You'll even discover how to use artificial neural networks and deep learning structures for classification! With such a rigorous grounding in so many topics, you will be an unbeatable data scientist by the end of the course.

Deep learning (DL) is advancing very quickly and different DL frameworks are effective at different tasks. As a result, we've used several DL frameworks at Uber ATG over the last few years. In 2016, Caffe2 was our primary deep learning framework, and in early 2017 we put in a significant amount of work to integrate TensorFlow. This involved major integration hurdles with CUDA and cuDNN, conflicts between dependencies of Caffe2 and TensorFlow, library loading issues and more. In late 2017, we started developing more models in PyTorch.

Data science, Artificial Intelligence (AI) and Machine Learning (ML), since last five to six years these phrases have made their places in Gartner's hype cycle curve. Gradually they have crossed the peak and moving toward the plateau. The curve also has few related terms such as Deep Neural Network, Cognitive AutoML etc. This shows that, there is an emerging technology trend around AI/ML which is going to prevail over the software industry during the coming years. Few of their predecessors such as Business Intelligence, Data Mining and Data Warehousing were there even before these years.

We were promised robots everywhere -- fully autonomous robots that will drive our cars end-to-end, clean our dishes, drive our freight, make our food, pipette and do our lab work, write our legal documents, mow the lawn, balance our books and even clean our houses. And yet instead of Terminator or WALL-E or HAL 9000 or R2-D2, all we got is Facebook serving us ads we don't want to click on, Netflix recommending us another movie that we probably shouldn't stay up to watch, and iRobot's Roomba. Where are all the robots? This is the question I've been trying to investigate while building my own robotics company (a currently stealth company named Chef Robotics in the food robotics space) as well as investing in many robotics/AI companies through my venture capital fund Prototype Capital. Industrial six degrees of freedom (read as six motors serially attached to each other) robot arms were actually developed around 1973 and there are hundreds of thousands of them out there -- it's just that up to this point, almost all of these robots have been in the extremely controlled environment of factory automation doing the same thing over and over again millions of times. And we've formed many multibillion dollar companies through these factory automation robots including FANUC, KUKA, ABB and Foxconn (yes they make their own robots). Go to any automotive manufacturing plant and you'll see hundreds (or in Tesla's case, thousands). They work insanely well and can pick up massive payloads -- a full car -- and have precision sometimes up to a millimeter.

Deep Instinct's platform is based on deep learning, the branch of AI that enables a computing system to process data and signals and organize the …

Convolutional Neural Network (CNN) might seem intimidating for a beginner. However, this project will provide an overview of how to build a model from scratch to detect pneumonia using Tensorflow and Keras. Pneumonia is a lung inflammation caused by a viral or bacterial infection that can range from mild to severe cases. This inflammation makes the patient unable to breathe enough oxygen to reach the bloodstream. It happens when an infection makes the air sacs (alveoli) in the lungs fill with fluid or pus that might affect either one or both lungs.

Introduction to machine learning: An early draft of a proposed textbook.