In this tutorial, you will learn how to train and test an end-to-end deep learning model for autonomous driving using data collected from the AirSim simulation environment. You will train a model to learn how to steer a car through a portion of the Mountain/Landscape map in AirSim using a single front facing webcam for visual input. Such a task is usually considered the "hello world" of autonomous driving, but after finishing this tutorial you will have enough background to start exploring new ideas on your own. Through the length of this tutorial, you will also learn some practical aspects and nuances of working with end-to-end deep learning methods. The code presented in this tutorial is written in Keras, a high-level deep learning Python API capable of running on top of CNTK, TensorFlow or Theano.

Over the course of an accumulated 10 hours spread out over two days of hearings, Mark Zuckerberg dodged question after question by citing the power of artificial intelligence. It's not even entirely clear what Zuckerberg means by "AI" here. He repeatedly brought up how Facebook's detection systems automatically take down 99 percent of "terrorist content" before any kind of flagging. In 2017, Facebook announced that it was "experimenting" with AI to detect language that "might be advocating for terrorism" -- presumably a deep learning technique. It's not clear that deep learning is actually part of Facebook's automated system.

People are, generally speaking, much better than computers at picking out a single voice in a crowd. You'll know this if you've ever tried to say something to your smart speaker while someone else is talking at the same time. Chances are it probably asked you to repeat your command. Now, this could be about to change, following the announcement Google has trained an AI model to separate distinct speech signals from one single audio recording. In a blog post, the company reveals its new deep learning model works by using both the auditory and visual signals of an input video – in short, it lip reads.

It's pretty clear that artificial intelligence will have a major impact on the future. We can already see the technology hard at work in self-driving cars and smart voice assistants. The AI & Deep Learning Bundle helps you master the code behind these amazing machines, with 8 ebooks and 41 video tutorials. Right now, you can pay what you like for the training (worth $691) at the PopSci Shop. From finance to healthcare, there are many potential uses for artificial intelligence.

The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of performance and energy efficiency. In the first part of this paper, the behaviour of the 12-bit fixed-point arithmetic when training a convolutional neural network with the CIFAR-10 dataset is analysed, showing that such arithmetic is not the most appropriate for the training phase. After that, the paper presents and evaluates, under the same conditions, alternative low-precision arithmetics, starting with the 12-bit floating-point arithmetic. These two representations are then leveraged using local scaling in order to increase accuracy and get closer to the baseline 32-bit floating-point arithmetic. Finally, the paper introduces a simplified model in which both the outputs and the gradients of the neural networks are constrained to power-of-two values, just using 7 bits for their representation. The evaluation demonstrates a minimal loss in accuracy for the proposed Power-of-Two neural network, avoiding the use of multiplications and divisions and thereby, significantly reducing the training time as well as the energy consumption and memory requirements during the training and inference phases.

In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To this end, our multi-variable LSTM equipped with tensorized hidden states is developed to learn variable specific representations, which give rise to both temporal and variable level attention. Preliminary experiments demonstrate comparable prediction performance of multi-variable LSTM w.r.t. encoder-decoder based baselines. More interestingly, variable importance in real datasets characterized by the variable attention is highly in line with that determined by statistical Granger causality test, which exhibits the prospect of multi-variable LSTM as a simple and uniform end-to-end framework for both forecasting and knowledge discovery.

In recent years, defending adversarial perturbations to natural examples in order to build robust machine learning models trained by deep neural networks (DNNs) has become an emerging research field in the conjunction of deep learning and security. In particular, MagNet consisting of an adversary detector and a data reformer is by far one of the strongest defenses in the black-box oblivious attack setting, where the attacker aims to craft transferable adversarial examples from an undefended DNN model to bypass an unknown defense module deployed on the same DNN model. Under this setting, MagNet can successfully defend a variety of attacks in DNNs, including the high-confidence adversarial examples generated by the Carlini and Wagner's attack based on the $L_2$ distortion metric. However, in this paper, under the same attack setting we show that adversarial examples crafted based on the $L_1$ distortion metric can easily bypass MagNet and mislead the target DNN image classifiers on MNIST and CIFAR-10. We also provide explanations on why the considered approach can yield adversarial examples with superior attack performance and conduct extensive experiments on variants of MagNet to verify its lack of robustness to $L_1$ distortion based attacks. Notably, our results substantially weaken the assumption of effective threat models on MagNet that require knowing the deployed defense technique when attacking DNNs (i.e., the gray-box attack setting).

The discovery of adversarial examples has raised concerns about the practical deployment of deep learning systems. In this paper, we argue that the field of medicine may be uniquely susceptible to adversarial attacks, both in terms of monetary incentives and technical vulnerability. To this end, we outline the healthcare economy and the incentives it creates for fraud, we extend adversarial attacks to three popular medical imaging tasks, and we provide concrete examples of how and why such attacks could be realistically carried out. For each of our representative medical deep learning classifiers, both white and black box attacks were both effective and human-imperceptible. We urge caution in employing deep learning systems in clinical settings, and encourage research into domain-specific defense strategies.

Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policies simultaneously in stochastic cooperative environments. This paper extends the recently proposed weighted double estimator to the multiagent domain and propose a multiagent DRL framework, named weighted double deep Q-network (WDDQN). By utilizing the weighted double estimator and the deep neural network, WDDQN can not only reduce the bias effectively but also be extended to scenarios with raw visual inputs. To achieve efficient cooperation in the multiagent domain, we introduce the lenient reward network and the scheduled replay strategy. Experiments show that the WDDQN outperforms the existing DRL and multiaent DRL algorithms, i.e., double DQN and lenient Q-learning, in terms of the average reward and the convergence rate in stochastic cooperative environments.

This paper presents an open-source enforcement learning toolkit named CytonRL (https://github.com/arthurxlw/cytonRL). The toolkit implements four recent advanced deep Q-learning algorithms from scratch using C++ and NVIDIA's GPU-accelerated libraries. The code is simple and elegant, owing to an open-source general-purpose neural network library named CytonLib. Benchmark shows that the toolkit achieves competitive performances on the popular Atari game of Breakout.