To learn Chinese in this room, talk to the floating panda head. The Mandarin-speaking avatar zips around a 360-degree restaurant scene in an artificial intelligence-driven instruction program that looks like a giant video game. Rensselaer Polytechnic Institute students testing the technology move inside the 12-foot-high, wrap-around projection to order virtual bean curd from the panda waiter, chat with Beijing market sellers and practice tai chi by mirroring moves of a watchful mentor. "Definitely less anxiety than messing it up with a real human being," says Rahul Divekar, a computer science graduate student working on the project. "So compared to that anxiety, this is a lot more easy."

Tom was discussing the film star Tang Wei with a chatbot named XiaoIce, and the bot was excited: "A goddess! She stole my heart … and then went off and married!" Married who? "Haven't you heard?" XiaoIce replied. "Tang Wei is engaged to famous Korean director Kim Tae-yong." XiaoIce is a massive hit on social networks in Asia. Introduced in 2014 by Microsoft Research and Bing in Beijing, it can answer simple questions, like a stripped-down version of Cortana.

Dubai Electricity and Water Authority (DEWA) is organising the AI Leadership Programme in cooperation with experts from the University of California, Berkeley. The programme is attended by DEWA's leadership and staff who specialise in Artificial Intelligence (AI). The programme supports DEWA's efforts to achieve the directives of the wise leadership to anticipate the future and keep pace with the Fourth Industrial Revolution. The 3-day programme covers the latest developments in AI application in energy, water, machine learning, data science and applications, and other related topics. Participants will also learn about virtual implementation of AI applications in the work environment.

The Drone Racing League (DRL) will host a series of races and competitions where autonomous drones will try to beat a professional drone pilot. Teams of university students and other drone enthusiasts will be invited to compete for more than $2 million. The Artificial Intelligence Robotic Racing (AIRR) Circuit will produce four AI vs. AI races in its inaugural season and will use the same video game-inspired courses as the kinds used by pro drone pilots in the DRL Allianz World Championship, DRL CEO Nicholas Horbaczewski told VentureBeat in an email. Both the AIRR Circuit and the AlphaPilot Innovation Challenge, which pits human versus machine, will take place during the 2019 season. The first drone from an autonomous team to beat a human will receive $250,000, and the winning team of the AIRR Circuit will receive $1 million.

Picture a reality where whether you are at work or picking up your child from school, someone is tracking exactly where you are and logging it away for analysis. On the way home, you stop at the grocery store and pick up a six-pack and a few snacks. Someone is tracking those activities, too. Then when you bring those snacks to a party that night with your friends, all your conversations are captured and logged as well. The next day you have a meeting with a loan officer at a bank where you're hoping to get the money you need to start a business you've been working toward creating for years but are denied.

Leveraging these insights, we propose a "heating-up" strategy to train a classifier To overcome the sampling issue, a variety of hard mining strategies (Schroff et al., 2015; Mishchuk In this paper, we show that the temperature parameter in the softmax function, defined by Hinton et al. (2015) for knowledge transfer, plays an important role in determining the distribution of the Compared to the state-of-the-art methods in deep metric learning, the proposed "heating-up" method Siamese networks with contrastive loss (Chopra et al., 2005) was one of the earliest attempts to solve A reasonable solution to address the sampling issue is mining samples that are the most informative for training, also known as "hard mining". Semihard mining (Schroff et al., 2015) tries to find triplets in a training batch, for which the distance of Lifted structured loss (Song et al., 2016) exploits all Proxy NCA (Movshovitz-Attias et al., 2017) proposes to learn semantic proxies for training data and Applying hard mining with proxies is more efficient than with samples. In face verification, quite a few works have shown that training a classifier and using the output of the second last layer as embedding performs reasonably well (Wang et al., 2017b). This paper shows that the scalar can be seen as the temperature parameter of the softmax function in Hinton et al. (2015). The proposed "heating-up" idea is based on an observation that different We define 2 types of training samples as in Figure 1.

Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult to impose or assess structural constraints such as conditional independence. We propose a framework for learning representations that relies on Auto-Encoding Variational Bayes and whose search space is constrained via kernel-based measures of independence. In particular, our method employs the d-variable Hilbert-Schmidt Independence Criterion (dHSIC) to enforce independence between the latent representations and arbitrary nuisance factors. We show how to apply this method to a range of problems, including the problems of learning invariant representations and the learning of interpretable representations. We also present a full-fledged application to single-cell RNA sequencing (scRNA-seq). In this setting the biological signal is mixed in complex ways with sequencing errors and sampling effects. We show that our method outperforms the state-of-the-art in this domain.

In a poisoning attack against a learning algorithm, an adversary tampers with a fraction of the training data $T$ with the goal of increasing the classification error of the constructed hypothesis/model over the final test distribution. In the distributed setting, $T$ might be gathered gradually from $m$ data providers $P_1,\dots,P_m$ who generate and submit their shares of $T$ in an online way. In this work, we initiate a formal study of $(k,p)$-poisoning attacks in which an adversary controls $k\in[n]$ of the parties, and even for each corrupted party $P_i$, the adversary submits some poisoned data $T'_i$ on behalf of $P_i$ that is still "$(1-p)$-close" to the correct data $T_i$ (e.g., $1-p$ fraction of $T'_i$ is still honestly generated). For $k=m$, this model becomes the traditional notion of poisoning, and for $p=1$ it coincides with the standard notion of corruption in multi-party computation. We prove that if there is an initial constant error for the generated hypothesis $h$, there is always a $(k,p)$-poisoning attacker who can decrease the confidence of $h$ (to have a small error), or alternatively increase the error of $h$, by $\Omega(p \cdot k/m)$. Our attacks can be implemented in polynomial time given samples from the correct data, and they use no wrong labels if the original distributions are not noisy. At a technical level, we prove a general lemma about biasing bounded functions $f(x_1,\dots,x_n)\in[0,1]$ through an attack model in which each block $x_i$ might be controlled by an adversary with marginal probability $p$ in an online way. When the probabilities are independent, this coincides with the model of $p$-tampering attacks, thus we call our model generalized $p$-tampering. We prove the power of such attacks by incorporating ideas from the context of coin-flipping attacks into the $p$-tampering model and generalize the results in both of these areas.

Elasticity images map biomechanical properties of soft tissues to aid in the detection and diagnosis of pathological states. In particular, quasi-static ultrasonic (US) elastography techniques use force-displacement measurements acquired during an US scan to parameterize the spatio-temporal stress-strain behavior. Current methods use a model-based inverse approach to estimate the parameters associated with a chosen constitutive model. However, model-based methods rely on simplifying assumptions of tissue biomechanical properties, often limiting elastography to imaging one or two linear-elastic parameters. We previously described a data-driven method for building neural network constitutive models (NNCMs) that learn stress-strain relationships from force-displacement data. Using measurements acquired on gelatin phantoms, we demonstrated the ability of NNCMs to characterize linear-elastic mechanical properties without an initial model assumption and thus circumvent the mathematical constraints typically encountered in classic model-based approaches to the inverse problem. While successful, we were required to use a priori knowledge of the internal object shape to define the spatial distribution of regions exhibiting different material properties. Here, we introduce Cartesian neural network constitutive models (CaNNCMs) that are capable of using data to model both linear-elastic mechanical properties and their distribution in space. We demonstrate the ability of CaNNCMs to capture arbitrary material property distributions using stress-strain data from simulated phantoms. Furthermore, we show that a trained CaNNCM can be used to reconstruct a Young's modulus image. CaNNCMs are an important step toward data-driven modeling and imaging the complex mechanical properties of soft tissues.

This paper addresses the problem of change-point detection on sequences of high-dimensional and heterogeneous observations, which also possess a periodic temporal structure. Due to the dimensionality problem, when the time between change-points is on the order of the dimension of the model parameters, drifts in the underlying distribution can be misidentified as changes. To overcome this limitation we assume that the observations lie in a lower dimensional manifold that admits a latent variable representation. In particular, we propose a hierarchical model that is computationally feasible, widely applicable to heterogeneous data and robust to missing instances. Additionally, to deal with the observations' periodic dependencies, we employ a circadian model where the data periodicity is captured by non-stationary covariance functions. We validate the proposed technique on synthetic examples and we demonstrate its utility in the detection of changes for human behavior characterization.