It is certainly an understatement to say that Rashida Hodge is an inspiration. A tenacious, 18-year tech exec, Hodge has forged an impressive career centered on exploration, expanding representation, and philanthropy. In her current role at IBM, Hodge leads product integration of artificial intelligence and other emerging technologies for key IBM clients in North America. Hodge's story will certainly motivate anyone who has the pleasure of meeting her but may be especially useful to women and people of color looking to begin a career in STEM. After our powerful discussion, it became clear that the natural choice was to let Hodge's story be told in her own, kind and confident voice. We began our conversation by discussing Hodge's childhood and early career, during which she explained how family support propelled her towards a love for and career in engineering.

The appeal of thinking machines, particularly those that seem human, is understandable. If we could create an intelligent being, it might relieve our loneliness, protect us from our enemies, cure our illnesses, comfort our griefs. Then again, it might just as easily turn on us, destroy us, and take over the world. Books, movies and other cultural representations of AI are shot through with this tension: Will the being we create be our savior or our crucifier? But the actual title was, "Frankenstein, or…" Or what?

The Reputed Garner Insights website offers vast reports on different market.They cover all industry and these reports are very precise and reliable. It also offers Artificial Intelligence (AI) in Automotive Market Report 2020 in its research report store. It is the most comprehensive report available on this market. The report study provides information on market trends and development, drivers, capacities, technologies, and on the changing investment structure of the Global Artificial Intelligence (AI) in Automotive Market. The study gives a transparent view on the Global Artificial Intelligence (AI) in Automotive Market and includes a thorough competitive scenario and portfolio of the key players functioning in it.

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of a backdoored network embed new features to detect the presence of a trigger and the subsequent classification layers learn to mispredict when triggers are detected. Therefore, to detect backdoors, the proposed defense uses two synergistic anomaly detectors trained on clean validation data: the first is a novelty detector that checks for anomalous features, while the second detects anomalous mappings from features to outputs by comparing with a separate classifier trained on validation data. The approach is evaluated on a wide range of backdoored networks (with multiple variations of triggers) that successfully evade state-of-the-art defenses. Additionally, we evaluate the robustness of our approach on imperceptible perturbations, scalability on large-scale datasets, and effectiveness under domain shift. This paper also shows that the defense can be further improved using data augmentation.

Autonomous robot-assisted feeding requires the ability to acquire a wide variety of food items. However, it is impossible for such a system to be trained on all types of food in existence. Therefore, a key challenge is choosing a manipulation strategy for a previously unseen food item. Previous work showed that the problem can be represented as a linear contextual bandit on visual information. However, food has a wide variety of multi-modal properties relevant to manipulation that can be hard to distinguish visually. Our key insight is that we can leverage the haptic information we collect during manipulation to learn some of these properties and more quickly adapt our visual model to previously unseen food. In general, we propose a modified linear contextual bandit framework augmented with post hoc context observed after action selection to empirically increase learning speed (as measured by cross-validation mean square error) and reduce cumulative regret. Experiments on synthetic data demonstrate that this effect is more pronounced when the dimensionality of the context is large relative to the post hoc context or when the post hoc context model is particularly easy to learn. Finally, we apply this framework to the bite acquisition problem and demonstrate the acquisition of 8 previously unseen types of food with 21% fewer failures across 64 attempts.

Throughout my half-decade of working at Well Good, I've become an accidental alternative milk connoisseur. Avocado milk, barley milk, pili nut milk, and chia milk have all made their way into my fridge at some point. So when I got a tip about yet another vegan option hitting store shelves, I had to admit, I was skeptical. Does the world really need another alt-milk?Jeff Bezos is betting on the answer to that question being yes. The Amazon CEO is backing a new product called NotMilk, created by NotCo, known as the "Impossible Foods" of Latin America.

Last August I decided to hire a journalist to produce content for a project. This person would help me with social media posts, newsletters and reports, with the goal of providing other journalists with scientific knowledge coming from social media. After a few weeks, having worked on the budget and the targets I had in mind, I pivoted the whole plan and hired two part-time developers to create a Twitter bot and an automated report delivery system. In one stroke, I solved two problems: feeding my project's Twitter timeline and providing newsletter content for the users. After the launch, no human hands needed to touch those two streams of content. It was a classic scenario in which automation literally stole a journalist's job.

Knowledge Graphs (KGs) have made a qualitative leap and effected a real revolution in knowledge representation. This is leveraged by the underlying structure of the KG which underpins a better comprehension, reasoning and interpreting of knowledge for both human and machine. Therefore, KGs continue to be used as a main driver to tackle a plethora of real-life problems in dissimilar domains. However, there is no consensus on a plausible and inclusive definition to domain KG. Further, in conjunction with several limitations and deficiencies, various domain KG construction approaches are far from perfection. This survey is the first to provide an inclusive definition to the notion of domain KG. Also, a comprehensive review of the state-of-the-art approaches drawn from academic works relevant to seven dissimilar domains of knowledge is provided. The scrutiny of the current approaches reveals a correlated array of limitations and deficiencies. The set of improvements to address the limitations of the current approaches are introduced followed by recommendations and opportunities for future research directions.

Financial institutions mostly deal with people. Therefore, characterizing different kinds of human behavior can greatly help institutions for improving their relation with customers and with regulatory offices. In many of such interactions, humans have some internal goals, and execute some actions within the financial system that lead them to achieve their goals. In this paper, we tackle these tasks as a behavior-traces classification task. An observer agent tries to learn characterizing other agents by observing their behavior when taking actions in a given environment. The other agents can be of several types and the goal of the observer is to identify the type of the other agent given a trace of observations. We present CABBOT, a learning technique that allows the agent to perform on-line classification of the type of planning agent whose behavior is observing. In this work, the observer agent has partial and noisy observability of the environment (state and actions of the other agents). In order to evaluate the performance of the learning technique, we have generated a domain-independent goal-based simulator of agents. We present experiments in several (both financial and non-financial) domains with promising results.

Route planning is important in transportation. Existing works focus on finding the shortest path solution or using metrics such as safety and energy consumption to determine the planning. It is noted that most of these studies rely on prior knowledge of road network, which may be not available in certain situations. In this paper, we design a route planning algorithm based on deep reinforcement learning (DRL) for pedestrians. We use travel time consumption as the metric, and plan the route by predicting pedestrian flow in the road network. We put an agent, which is an intelligent robot, on a virtual map. Different from previous studies, our approach assumes that the agent does not need any prior information about road network, but simply relies on the interaction with the environment. We propose a dynamically adjustable route planning (DARP) algorithm, where the agent learns strategies through a dueling deep Q network to avoid congested roads. Simulation results show that the DARP algorithm saves 52% of the time under congestion condition when compared with traditional shortest path planning algorithms.