We study the global convergence and global optimality of actor-critic, one of the most popular families of reinforcement learning algorithms. While most existing works on actor-critic employ bi-level or two-timescale updates, we focus on the more practical single-timescale setting, where the actor and critic are updated simultaneously. Specifically, in each iteration, the critic update is obtained by applying the Bellman evaluation operator only once while the actor is updated in the policy gradient direction computed using the critic. Moreover, we consider two function approximation settings where both the actor and critic are represented by linear or deep neural networks. For both cases, we prove that the actor sequence converges to a globally optimal policy at a sublinear $O(K^{-1/2})$ rate, where $K$ is the number of iterations. To the best of our knowledge, we establish the rate of convergence and global optimality of single-timescale actor-critic with linear function approximation for the first time. Moreover, under the broader scope of policy optimization with nonlinear function approximation, we prove that actor-critic with deep neural network finds the globally optimal policy at a sublinear rate for the first time.

Model interpretation is essential in data mining and knowledge discovery. It can help understand the intrinsic model working mechanism and check if the model has undesired characteristics. A popular way of performing model interpretation is Instance-wise Feature Selection (IFS), which provides an importance score of each feature representing the data samples to explain how the model generates the specific output. In this paper, we propose a Model-agnostic Effective Efficient Direct (MEED) IFS framework for model interpretation, mitigating concerns about sanity, combinatorial shortcuts, model identifiability, and information transmission. Also, we focus on the following setting: using selected features to directly predict the output of the given model, which serves as a primary evaluation metric for model-interpretation methods. Apart from the features, we involve the output of the given model as an additional input to learn an explainer based on more accurate information. To learn the explainer, besides fidelity, we propose an Adversarial Infidelity Learning (AIL) mechanism to boost the explanation learning by screening relatively unimportant features. Through theoretical and experimental analysis, we show that our AIL mechanism can help learn the desired conditional distribution between selected features and targets. Moreover, we extend our framework by integrating efficient interpretation methods as proper priors to provide a warm start. Comprehensive empirical evaluation results are provided by quantitative metrics and human evaluation to demonstrate the effectiveness and superiority of our proposed method. Our code is publicly available online at https://github.com/langlrsw/MEED.

Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the most interesting cases are targeted attacks, in which an attacker aims to force the system into recognizing given target transcriptions in an arbitrary audio sample. The increasing number of sophisticated, quasi imperceptible attacks raises the question of countermeasures. In this paper, we focus on hybrid ASR systems and compare four acoustic models regarding their ability to indicate uncertainty under attack: a feed-forward neural network and three neural networks specifically designed for uncertainty quantification, namely a Bayesian neural network, Monte Carlo dropout, and a deep ensemble. We employ uncertainty measures of the acoustic model to construct a simple one-class classification model for assessing whether inputs are benign or adversarial. Based on this approach, we are able to detect adversarial examples with an area under the receiving operator curve score of more than 0.99. The neural networks for uncertainty quantification simultaneously diminish the vulnerability to the attack, which is reflected in a lower recognition accuracy of the malicious target text in comparison to a standard hybrid ASR system.

Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequential recommendation problem, intending to predict the next items that the user might be interacted with. Recent works usually give an overall embedding from a user's behavior sequence. However, a unified user embedding cannot reflect the user's multiple interests during a period. In this paper, we propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec. Our multi-interest module captures multiple interests from user behavior sequences, which can be exploited for retrieving candidate items from the large-scale item pool. These items are then fed into an aggregation module to obtain the overall recommendation. The aggregation module leverages a controllable factor to balance the recommendation accuracy and diversity. We conduct experiments for the sequential recommendation on two real-world datasets, Amazon and Taobao. Experimental results demonstrate that our framework achieves significant improvements over state-of-the-art models. Our framework has also been successfully deployed on the offline Alibaba distributed cloud platform.

Just one day after TensorFlow hit version 2.3, Facebook's challenger project PyTorch was updated to 1.6, sporting support for automatic mixed precision training and a changed classification scheme for new features. The classification system will fall into one of three categories: stable, beta, or prototype. Beta corresponds to what had been known as experimental features, meaning there is a proven added value, but the API could still change or there are performance or coverage issues yet to tackle. Examples for features in this category include custom C classes, named tensors, and PyTorch Mobile. Prototypes are meant for getting "high bandwidth" feedback on the utility of a proposed new feature in order to either commit to getting it to beta or let it fall by the wayside. Prototypes aren't part of a binary and only available for those building from source or using nightlies or the associated compiler flag, which is why a couple of neat additions such as a profiler for distributed training or graph mode quantisation are a bit trickier to access.

AI applications in healthcare can literally change patients' lives, improving diagnostics and treatment and helping patients and healthcare providers make informed decisions quickly. AI in the global healthcare market (the total value of products and services sold) was valued at $2.4 billion in 2019 and is projected to reach $31.02 billion in 2025. Now in the COVID-19 pandemic, AI is being leveraged to identify virus-related misinformation on social media and remove it. AI is also helping scientists expedite vaccine development, track the virus and understand individual and population risk, among other applications. Companies such as Microsoft, which recently stated it will dedicate $20 million to advance the use of artificial intelligence in COVID-19 research, recognize the need for and extraordinary potential of AI in healthcare.

This past spring, as billions of people languished at home under lockdown and stared at gloomy graphs, Linda Wang and Alexander Wong, scientists at DarwinAI, a Canadian startup that works in the field of artificial intelligence, took advantage of their enforced break: In collaboration with the University of Waterloo, they helped develop a tool to detect COVID-19 infection by means of X-rays. Using a database of thousands of images of lungs, COVID-Net – as they called the open-access artificial neural network – can detect with 91 percent certainty who is ill with the virus. In the past, we would undoubtedly have been suspicious of, or at least surprised by, a young company (DarwinAI was established in 2018) with no connection to radiology, having devised such an ambitious tool within mere weeks. But these days, we know it can be done. Networks that draw on an analysis of visual data using a technique known as "deep learning" can, with relative flexibility, adapt themselves to decipher any type of image and provide results that often surpass those obtained by expert radiologists.

You might be wondering why I started first with the need for data augmentation rather than its meaning, but that's the best way to learn anything quickly. So, let dive into Data Augmentation. Training DATA is the backbone of an entire Deep Learning project, more the data, more the features that can be extracted, and thus better the accuracy of the model. Deep Learning models are directly dependent on the amount of data, but it's not always that we have sufficient data to train our images. This problem is best solved by data augmentation.

Online Courses Udemy - A Complete Guide on TensorFlow 2.0 using Keras API, Build Amazing Applications of Deep Learning and Artificial Intelligence in TensorFlow 2.0 Created by Hadelin de Ponteves, Kirill Eremenko, SuperDataScience Team, Luka Anicin English [Auto] Students also bought Machine Learning A-Z: Hands-On Python & R In Data Science Data Analysis & Visualization Bootcamp - 2020 BESTSELLER R Programming A-Z: R For Data Science With Real Exercises! Practical Machine Learning by Example in Python Python for Statistical Analysis Preview this course GET COUPON CODE Description Welcome to Tensorflow 2.0! TensorFlow 2.0 has just been released, and it introduced many features that simplify the model development and maintenance processes. From the educational side, it boosts people's understanding by simplifying many complex concepts. From the industry point of view, models are much easier to understand, maintain, and develop.

Create a pipeline to remove stop-words,perform tokenization and padding. In this hands-on project, we will train a Bidirectional Neural Network and LSTM based deep learning model to detect fake news from a given news corpus. This project could be practically used by any media company to automatically predict whether the circulating news is fake or not. The process could be done automatically without having humans manually review thousands of news related articles. Note: This course works best for learners who are based in the North America region.