Google today made available TensorFlow RunTime (TFRT), a new runtime for its TensorFlow machine learning framework that provides a unified, extensible infrastructure layer with high performance across a range of hardware. Its release in open source on GitHub follows a preview earlier this year during a session at the 2020 TensorFlow Dev Summit, where TFRT was shown to speed up core loops in a key benchmarking test. TFRT is intended to address the needs of data scientists looking for faster model iteration time and better error reporting, Google says, as well as app developers looking for improved performance while training and serving models in production. Tangibly, TFRT could reduce the time it takes to develop, validate, and deploy an enterprise-scale model, which surveys suggest can range from weeks to months (or years). And it might beat back Facebook's encroaching PyTorch framework, which continues to see rapid uptake among companies like OpenAI, Preferred Networks, and Uber.

If you're new to all this deep learning stuff, then don't worry--we'll take you through it all step by step. We do however assume that you've been coding for at least a year, and also that (if you haven't used Python before) you'll be putting in the extra time to learn whatever Python you need as you go. You might be surprised by what you don't need to become a top deep learning practitioner. You need one year of coding experience, a GPU and appropriate software (see below), and that's it. You don't need much data, you don't need university-level math, and you don't need a giant data center.

Document processing is a critical task across virtually every industry. At Element AI, we're developing new tools to accelerate and even automate this process. We leverage state-of-the-art deep learning techniques to build systems that can precisely and rapidly extract information from digital and scanned documents. This requires models that have the ability to understand 2D layout and the semantics of text. The heterogeneity inherent in this type of data poses many challenges.

Every week, Invector Labs publishes a newsletter that covers the most recent developments in AI research and technology. You can find this week's issue below. You can sign up for it below. Interpretability remains one of the biggest challenges in modern machine learning. Disciplines such as deep learning have increase the sophistication of neural networks but that sophistication has introduced challenges in terms of understanding how these systems make decisions.

This means only one thing; you need to be prepared for constant learning. With all the abundance of abstract terms and an almost infinite number of details, the AI and ML learning curve can indeed be steep for many. But, getting started with anything new is hard, isn't it? Moreover, I believe everyone can learn it if only there is a strong desire. Besides, there is an effective approach that will facilitate your learning.

Researchers in Korea have developed a convolutional neural network (CNN) architecture capable of aiding specialists in the diagnosis of 134 skin disorders. Their algorithm can also predict treatment options. With the assistance of this method, the team found that the diagnostic accuracy of dermatologists as well as the general public was significantly improved. The neural network was trained with 220,680 images of 174 disorders and validated using Edinburgh (1,300 images; 10 disorders) and Seoul National University datasets (2,201 images; 134 disorders). The datasets consisted of images of Asians and Caucasians.

Recently machine learning techniques have become popular for analysing physical systems and solving problems occurring in quantum computing. In this paper we focus on using such techniques for finding the sequence of physical operations implementing the given quantum logical operation. In this context we analyse the flexibility of the data representation and compare the applicability of two machine learning approaches based on different representations of data. We demonstrate that the utilization of the geometrical structure of control pulses is sufficient for achieving high-fidelity of the implemented evolution. We also demonstrate that artificial neural networks, unlike geometrical methods, posses the generalization abilities enabling them to generate control pulses for the systems with variable strength of the disturbance. The presented results suggest that in some quantum control scenarios, geometrical data representation and processing is competitive to more complex methods.

Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input $x$ and associated target $y$, EP proceeds in two phases: in the first phase neurons evolve freely towards a first steady state; in the second phase output neurons are nudged towards $y$ until they reach a second steady state. However, in existing implementations of EP, the learning rule is not local in time: the weight update is performed after the dynamics of the second phase have converged and requires information of the first phase that is no longer available physically. In this work, we propose a version of EP named Continual Equilibrium Propagation (C-EP) where neuron and synapse dynamics occur simultaneously throughout the second phase, so that the weight update becomes local in time. Such a learning rule local both in space and time opens the possibility of an extremely energy efficient hardware implementation of EP. We prove theoretically that, provided the learning rates are sufficiently small, at each time step of the second phase the dynamics of neurons and synapses follow the gradients of the loss given by BPTT (Theorem 1). We demonstrate training with C-EP on MNIST and generalize C-EP to neural networks where neurons are connected by asymmetric connections. We show through experiments that the more the network updates follows the gradients of BPTT, the best it performs in terms of training. These results bring EP a step closer to biology by better complying with hardware constraints while maintaining its intimate link with backpropagation.

As gradual typing becomes increasingly popular in languages like Python and TypeScript, there is a growing need to infer type annotations automatically. While type annotations help with tasks like code completion and static error catching, these annotations cannot be fully determined by compilers and are tedious to annotate by hand. This paper proposes a probabilistic type inference scheme for TypeScript based on a graph neural network. Our approach first uses lightweight source code analysis to generate a program abstraction called a type dependency graph, which links type variables with logical constraints as well as name and usage information. Given this program abstraction, we then use a graph neural network to propagate information between related type variables and eventually make type predictions. Our neural architecture can predict both standard types, like number or string, as well as user-defined types that have not been encountered during training. Our experimental results show that our approach outperforms prior work in this space by $14\%$ (absolute) on library types, while having the ability to make type predictions that are out of scope for existing techniques.