While research on adversarial examples in machine learning for images has been prolific, similar attacks on deep learning (DL) for radio frequency (RF) signals and their mitigation strategies are scarcely addressed in the published work, with only one recent publication in the RF domain [1]. RF adversarial examples (AdExs) can cause drastic, targeted misclassification results mostly in spectrum sensing/ survey applications (e.g. BPSK mistaken for 8-PSK) with minimal waveform perturbation. It is not clear if the RF AdExs maintain their effects in the physical world, i.e., when AdExs are delivered over-the-air (OTA). Our research on deep learning AdExs and proposed defense mechanisms are RF-centric, and incorporate physical world, OTA effects. We here present defense mechanisms based on statistical tests. One test to detect AdExs utilizes Peak-to- Average-Power-Ratio (PAPR) of the DL data points delivered OTA, while another statistical test uses the Softmax outputs of the DL classifier, which corresponds to the probabilities the classifier assigns to each of the trained classes. The former test leverages the RF nature of the data, and the latter is universally applicable to AdExs regardless of their origin. Both solutions are shown as viable mitigation methods to subvert adversarial attacks against communications and radar sensing systems.

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully shape reward function to guide policy optimization. This limits the applicability of RL in the real world since both reinforcement learning and domain-specific knowledge are required. It is therefore of great practical importance to develop algorithms which can learn from a binary signal indicating successful task completion or other unshaped, sparse reward signals. We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents. Our method complements the recently proposed hindsight experience replay (HER) by inducing an automatic exploratory curriculum. We evaluate our approach on the tasks of reaching various goal locations in an ant maze and manipulating objects with a robotic arm. Each task provides only binary rewards indicating whether or not the goal is achieved. Our method asymmetrically augments these sparse rewards for a pair of agents each learning the same task, creating a competitive game designed to drive exploration. Extensive experiments demonstrate that this method leads to faster converge and improved task performance.

Abstract--In order to maximize detection precision rate as well as the recall rate, this paper proposes an in-vehicle multisource fusionscheme in Keyword Spotting (KWS) System for vehicle applications. Vehicle information, as a new source for the original system, is collected by an in-vehicle data acquisition platform while the user is driving. A Deep Neural Network (DNN) is trained to extract acoustic features and make a speech classification. Based on the posterior probabilities obtained from DNN, the vehicle information including the speed and direction of vehicle is applied to choose the suitable parameter from a pair of sensitivity values for the KWS system. The experimental results show that the KWS system with the proposed multi-source fusion scheme can achieve better performances in term of precision rate, recall rate, and mean square error compared to the system without it. I. INTRODUCTION Keyword Spotting (KWS) System, also known as wakeword detection,refers to the task of detecting specified keyword from a continuous stream of audio provided by the users [1]. Keyword Spotting has been an active research area in speech recognition for decades, and widely used in numerous applications.

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.

Big Data and artificial intelligence (AI) have brought many advantages to businesses in recent years. But with these advances comes a raft of new terminology that we all have to get to grips with. As a result, some business users are left unsure of the difference between terms, or use terms with different meanings interchangeably. 'Neural networks' and'deep learning' are two such terms that I've noticed people using interchangeably, even though there's a difference between the two. Therefore, in this article, I define both neural networks and deep learning, and look at how they differ.

AI research quickly accelerated, with Kunihiko Fukushima developing the first true, multilayered neural network in 1975. The original goal of the neural network approach was to create a computational system that could solve problems like a human brain. However, over time, researchers shifted their focus to using neural networks to match specific tasks, leading to deviations from a strictly biological approach. Since then, neural networks have supported diverse tasks, including computer vision, speech recognition, machine translation, social network filtering, playing board and video games, and medical diagnosis. As structured and unstructured data sizes increased to big data levels, people developed deep learning systems, which are essentially neural networks with many layers.

The spread of fake news is already a very real problem. Artificial intelligence could make the problem even worse. That prospect is so frightening that an Elon Musk-backed non-profit called OpenAI has decided not to publicly circulate AI-based text generation technology that enables researchers to spin an all-too-convincing--and yes, fabricated--machine-written article. "Due to our concerns about malicious applications of the technology, we are not releasing the trained model," OpenAI blogged. Such concerns go beyond just generating misleading news articles.

Click to learn more about author Rosaria Silipo. Automatic machine translation has been a popular subject for machine learning algorithms. After all, if machines can detect topics and understand texts, translation should be just the next step. Machine translation can be seen as a variation of natural language generation. In a previous project, we worked on the automatic generation of fairy tales (see "Once upon a Time … by LSTM Network").

Recycling is NOT good for the world. It is bad for the environment, it is bad for our health, and it is bad for our economy. These are the words of GPT-2, an artificially intelligent super-troll. It needs just a few words to prompt a rant hundreds of words long on almost any topic and its creators say it may be too dangerous to release to the public because of potential misuse. However, these fears are overblown.

Amgen's drug discovery group is a few blocks beyond that. Until recently, Barzilay, one of the world's leading researchers in artificial intelligence, hadn't given much thought to these nearby buildings full of chemists and biologists. But as AI and machine learning began to perform ever more impressive feats in image recognition and language comprehension, she began to wonder: could it also transform the task of finding new drugs? The problem is that human researchers can explore only a tiny slice of what is possible. It's estimated that there are as many as 1060 potentially drug-like molecules--more than the number of atoms in the solar system. But traversing seemingly unlimited possibilities is what machine learning is good at. Trained on large databases of existing molecules and their properties, the programs can explore all possible related molecules.