Classification of large multivariate time series with strong class imbalance is an important task in real-world applications. Standard methods of class weights, oversampling, or parametric data augmentation do not always yield significant improvements for predicting minority classes of interest. Non-parametric data augmentation with Generative Adversarial Networks (GANs) offers a promising solution. We propose Imputation Balanced GAN (IB-GAN), a novel method that joins data augmentation and classification in a one-step process via an imputation-balancing approach. IB-GAN uses imputation and resampling techniques to generate higher quality samples from randomly masked vectors than from white noise, and augments classification through a class-balanced set of real and synthetic samples. Imputation hyperparameter $p_{miss}$ allows for regularization of classifier variability by tuning innovations introduced via generator imputation. IB-GAN is simple to train and model-agnostic, pairing any deep learning classifier with a generator-discriminator duo and resulting in higher accuracy for under-observed classes. Empirical experiments on open-source UCR data and proprietary 90K product dataset show significant performance gains against state-of-the-art parametric and GAN baselines.

Recurrent neural networks (RNNs) are wide-spread machine learning tools for modeling sequential and time series data. They are notoriously hard to train because their loss gradients backpropagated in time tend to saturate or diverge during training. This is known as the exploding and vanishing gradient problem. Previous solutions to this issue either built on rather complicated, purpose-engineered architectures with gated memory buffers, or - more recently - imposed constraints that ensure convergence to a fixed point or restrict (the eigenspectrum of) the recurrence matrix. Such constraints, however, convey severe limitations on the expressivity of the RNN. Essential intrinsic dynamics such as multistability or chaos are disabled. This is inherently at disaccord with the chaotic nature of many, if not most, time series encountered in nature and society. Here we offer a comprehensive theoretical treatment of this problem by relating the loss gradients during RNN training to the Lyapunov spectrum of RNN-generated orbits. We mathematically prove that RNNs producing stable equilibrium or cyclic behavior have bounded gradients, whereas the gradients of RNNs with chaotic dynamics always diverge. Based on these analyses and insights, we offer an effective yet simple training technique for chaotic data and guidance on how to choose relevant hyperparameters according to the Lyapunov spectrum.

Recently, the stability of graph filters has been studied as one of the key theoretical properties driving the highly successful graph convolutional neural networks (GCNs). The stability of a graph filter characterizes the effect of topology perturbation on the output of a graph filter, a fundamental building block for GCNs. Many existing results have focused on the regime of small perturbation with a small number of edge rewires. However, the number of edge rewires can be large in many applications. To study the latter case, this work departs from the previous analysis and proves a bound on the stability of graph filter relying on the filter's frequency response. Assuming the graph filter is low pass, we show that the stability of the filter depends on perturbation to the community structure. As an application, we show that for stochastic block model graphs, the graph filter distance converges to zero when the number of nodes approaches infinity. Numerical simulations validate our findings.

Amazon SageMaker is a fully managed service that enables developers and data scientists to quickly and easily build, train, and deploy machine learning (ML) models at any scale. Typically, you can use the pre-built and optimized training and inference containers that have been optimized for AWS hardware. Although those containers cover many deep learning workloads, you may have use cases where you want to use a different framework or otherwise customize the contents of your OS libraries within the container. To accommodate this, SageMaker provides the flexibility to train models using any framework that can run in a Docker container. This functionality enables you to use existing SageMaker training capabilities such as training jobs, hyperparameter tuning, and Managed Spot Training.

A lot of times when you read about deepfakes (more professionally known as synthetic media) the common themes being explored is only one of the two faces of deepfakes the negative side, however, I want to explore some of the positive things deepfakes can be used for so you can get a full scope of the capabilities of deepfakes. Glad you asked, simple answer: artificial intelligence-generated media that has seamlessly stitch anyone in the world into a video or photo they never actually in and a summarised more technical answer: deepfakes are made by using a GAN (generative adversarial network) a type of deep learning artificial intelligence. It uses two neural networks that rival each other to generate a synthetic version of data that can pass for real data, one of the neural networks is called the generator (generates new data instances) and the other is called a discriminator (evaluates them for authenticity). The purpose of the generator is to generate synthetic media that is given to the discriminator, which its purpose is to identify whether the media is fake or real, they are trained together until it achieves acceptable accuracy (discriminator fooled 50% of the time). So now that we have a better understanding of how deepfakes are created we can begin to explore the positive uses of deepfakes.

In this article we will tackle the task of information extraction from semi-structured data (documents). We shortly cover the difficulties posed by the semi-structured nature of documents as well as the current solutions to ensure better extraction results. Paper documents are still an integral part of all areas of life. They appear in everyday life as invoices, contracts or user manuals. Their structure, purpose and content can therefore vary greatly.

Artificial Intelligence is at its simplest, is intelligence demonstrated by Machines. It is a computer system that can perform tasks that ordinarily require human intelligence or human interference. Today, we will take a look at some of the domains of Artificial Intelligence, and a few examples. Machine Learning: As a subset of Artificial Intelligence, Machine learning allows software applications to become more accurate at predicting outcomes without being especially programmed for it. Its algorithms use historical data as input to predict new output values.

In this course we are going to look at NLP (natural language processing) with deep learning. Previously, you learned about some of the basics, like how many NLP problems are just regular machine learning and data science problems in disguise, and simple, practical methods like bag-of-words and term-document matrices. These allowed us to do some pretty cool things, like detect spam emails, write poetry, spin articles, and group together similar words. In this course I'm going to show you how to do even more awesome things. We'll learn not just 1, but 4 new architectures in this course.

The nifty app CamFind has come a long way with its artificial intelligence. It uses image recognition to identify an object when you point your smartphone camera at it. But back in 2015 its algorithms were less advanced: The app mostly used contract workers in the Philippines to quickly type what they saw through a user's phone camera, CamFind's co-founder confirmed to me recently. You wouldn't have guessed that from a press release it put out that year which touted industry-leading "deep learning technology," but didn't mention any human labelers. The practice of hiding human input in AI systems still remains an open secret among those who work in machine learning and AI. A 2019 analysis of tech startups in Europe by London-based MMC Ventures even found that 40% of purported AI startups showed no evidence of actually using artificial intelligence in their products.

The Transform Technology Summits start October 13th with Low-Code/No Code: Enabling Enterprise Agility. Register now! DeepMind wants to enable neural networks to emulate algorithms to get the best of both worlds, and it’s using Google Maps as a testbed. Classical algorithms are what have enabled software to eat the world, but the data they work with does not always reflect the real world. Deep learning is what powers some of the most iconic AI applications today, but deep learning models need retraining to be applied in domains they were not originally designed for. DeepMind is trying to co...