Using electrocardiograms as an example, we demonstrate the characteristic problems that arise when modeling one-dimensional signals containing inaccurate repeating pattern by means of standard convolutional networks. We show that these problems are systemic in nature. They are due to how convolutional networks work with composite objects, parts of which are not fixed rigidly, but have significant mobility. We also demonstrate some counterintuitive effects related to generalization in deep networks.

Variational Bayesian phylogenetic inference (VBPI) provides a promising general variational framework for efficient estimation of phylogenetic posteriors. However, the current diagonal Lognormal branch length approximation would significantly restrict the quality of the approximating distributions. In this paper, we propose a new type of VBPI, VBPI-NF, as a first step to empower phylogenetic posterior estimation with deep learning techniques. By handling the non-Euclidean branch length space of phylogenetic models with carefully designed permutation equivariant transformations, VBPI-NF uses normalizing flows to provide a rich family of flexible branch length distributions that generalize across different tree topologies. We show that VBPI-NF significantly improves upon the vanilla VBPI on a benchmark of challenging real data Bayesian phylogenetic inference problems. Further investigation also reveals that the structured parameterization in those permutation equivariant transformations can provide additional amortization benefit.

Neural network forms the foundation of deep learning and numerous AI applications. Classical neural networks are fully connected, expensive to train and prone to overfitting. Sparse networks tend to have convoluted structure search, suboptimal performance and limited usage. We proposed the novel uniform sparse network (USN) with even and sparse connectivity within each layer. USN has one striking property that its performance is independent of the substantial topology variation and enormous model space, thus offers a search-free solution to all above mentioned issues of neural networks. USN consistently and substantially outperforms the state-of-the-art sparse network models in prediction accuracy, speed and robustness. It even achieves higher prediction accuracy than the fully connected network with only 0.55% parameters and 1/4 computing time and resources. Importantly, USN is conceptually simple as a natural generalization of fully connected network with multiple improvements in accuracy, robustness and scalability. USN can replace the latter in a range of applications, data types and deep learning architectures. We have made USN open source at https://github.com/datapplab/sparsenet.

It's these genetic definitions that circumscribe their three-dimensional structures, which in turn determines their capabilities. But protein "folding," as it's called, is notoriously difficult to figure out from a corresponding genetic sequence alone. DNA contains only information about chains of amino acid residues and not those chains' final form. In December 2018, DeepMind attempted to tackle the challenge of protein folding with a machine learning system called AlphaFold. The product of two years of work, the Alphabet subsidiary said at the time that AlphaFold could predict structures more precisely than prior solutions.

Over the past few years, a team of Amazon scientists has been developing a book that is gaining popularity with students and developers attracted to the booming field of deep learning, a subset of machine learning focused on large-scale artificial neural networks. Called Dive into Deep Learning, the book arrives in a unique form factor, integrating text, mathematics, and runnable code. Drafted entirely through Jupyter notebooks, the book is a fully open source living document, with each update triggering updates to the PDF, HTML, and notebook versions. Its authors are Aston Zhang, an AWS senior applied scientist; Zachary Lipton, an AWS scientist and assistant professor of Operations Research and Machine Learning at Carnegie Mellon University; Mu Li, AWS principal scientist; and Alex Smola, AWS vice president and distinguished scientist. Dive into Deep Learning now supports @TensorFlow.

ServiceNow Inc. is beefing up its artificial intelligence development capabilities with the acquisition today of a company called Element AI Inc. that's widely known as one of the pioneers in the field. Montreal-based Element AI launched back in 2016 as a professional services firm focused on helping traditional enterprises implement machine learning. The startup garnered significant industry attention from the outset thanks in part to its high-profile co-founder, the well-known deep learning researcher Yoshua Bengio, who won the Turing Award in 2018 for his contributions to the field. Element AI has gradually expanded its focus since its launch by creating a fund to support fellow machine learning companies and introducing ready-made AI tools. The company's offerings include Knowledge Scout, a search engine for manufacturers that speeds up the diagnosis and repair of production line issues by giving technicians relevant information about previous incidents with similar characteristics.

Kubernetes is one of the most important pieces of software produced in the last decade and one of the most influential open source projects ever. Kubernetes has completely revolutionized how applications are developed and how infrastructure is deployed and managed. With Kubernetes' explosive rise, more and more physical hardware is being managed by Kubernetes. This trend has coincided with an explosion in the popularity of deep learning, an extremely computation-demanding technology that can result in a single data scientist occupying dozens of GPUs for weeks at a time. Give data scientists access to more hardware.

Alphabet-owned DeepMind may be best known for building the AI that beat a world-class Go player, but the company announced another, perhaps more vital breakthrough this morning. As part of its work for the 14th Critical Assessment of Protein Structure Prediction, or CASP, DeepMind's AlphaFold 2 AI has shown it can guess how certain proteins will fold themselves with surprising accuracy. In some cases, the results were perceived to be "competitive" with actual, experimental data. "We have been stuck on this one problem – how do proteins fold up – for nearly 50 years," said Professor John Moult, CASP chair and co-founder, in a DeepMind blog post. "To see DeepMind produce a solution for this, having worked personally on this problem for so long and after so many stops and starts, wondering if we'd ever get there, is a very special moment."

Artificial intelligence (AI) and machine learning, which is a subset of AI, are opening new opportunities in essentially all businesses, in addition to making frequently used equipment more capable. As anyone might expect, AI and machine learning are frequently applied to robots to improve them. Robots used in the industrial sector can assist organizations in completing more things with fewer blunders. Obviously, safety is key while adding robots in the work environment which is the reason some AI robotics organizations are creating solutions where robots can comprehend what's in their current environment and respond likewise. Veo Robotics has an industrial robotics system that consolidates computer vision, AI and sensors.

We can all agree that slow-motion videos create this dramatic effect, which certainly adds an extra flavor to specific scenes. On the other hand, slowing down a video might create several unwanted artifacts, which could deem it unwatchable. But what makes a slow-motion video great? Let's use Deep Learning for free, to produce the smooth result of a high-end camera capable of recording at high frame-rates Among other things, I would argue that the most important aspect is its FPS count: how many frames per second are rendered to the screen. Thus, we need to have an expensive camera able to record at a high frame-rate.