Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we describe a new recommender algorithm that explicitly models negative user preferences in order to recommend more positive items at the top of recommendation-lists. We build upon existing machine-learning model to incorporate the contextual information provided by negative user preference. With experimental evaluations on two openly available datasets, we show that our method is able to improve recommendation quality: by improving accuracy and at the same time reducing the number of negative items at the top of recommendation-lists. Our work demonstrates the value of the contextual information provided by negative feedback, and can also be extended to signed social networks and link prediction in other networks.

Zeroth-order optimization or derivative-free optimization is an important research topic in machine learning. In recent, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract Hessian information of the model function. In this paper, we utilize the second-order information of the objective function and propose a novel \emph{Hessian-aware zeroth-order algorithm} called \texttt{ZO-HessAware}. Our theoretical result shows that \texttt{ZO-HessAware} has an improved zeroth-order convergence rate and query complexity under structured Hessian approximation, where we propose a few approximation methods of such. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity.

In this paper, we propose a novel meta-learning method in a reinforcement learning setting, based on evolution strategies (ES), exploration in parameter space and deterministic policy gradients. ES methods are easy to parallelize, which is desirable for modern training architectures; however, such methods typically require a huge number of samples for effective training. We use deterministic policy gradients during adaptation and other techniques to compensate for the sample-efficiency problem while maintaining the inherent scalability of ES methods. We demonstrate that our method achieves good results compared to gradient-based meta-learning in high-dimensional control tasks in the MuJoCo simulator. In addition, because of gradient-free methods in the meta-training phase, which do not need information about gradients and policies in adaptation training, we predict and confirm our algorithm performs better in tasks that need multi-step adaptation.

For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary $\mathcal D=\{B_i\}_i^D$ of 3D basis poses. During testing, the detected 2D pose $Y$ is matched to dictionary by $Y \approx \sum_i M_i B_i$ where $\{M_i\}_i^D=\{c_i \Pi R_i\}$, by estimating the rotation $R_i$, projection $\Pi$ and sparse combination coefficients $c \in \mathbb R_{+}^D$. In this paper, we propose non-convex regularization $H(c)$ to learn coefficients $c$, including novel leaky capped $\ell_1$-norm regularization (LCNR), \begin{align*} H(c)=\alpha \sum_{i } \min(|c_i|,\tau)+ \beta \sum_{i } \max(| c_i|,\tau), \end{align*} where $0\leq \beta \leq \alpha$ and $0<\tau$ is a certain threshold, so the invalid components smaller than $\tau$ are composed with larger regularization and other valid components with smaller regularization. We propose a multi-stage optimizer with convex relaxation and ADMM. We prove that the estimation error $\mathcal L(l)$ decays w.r.t. the stages $l$, \begin{align*} Pr\left(\mathcal L(l) < \rho^{l-1} \mathcal L(0) + \delta \right) \geq 1- \epsilon, \end{align*} where $0< \rho <1, 0<\delta, 0<\epsilon \ll 1$. Experiments on large 3D human datasets like H36M are conducted to support our improvement upon previous approaches. To the best of our knowledge, this is the first theoretical analysis in this line of research, to understand how the recovery error is affected by fundamental factors, e.g. dictionary size, observation noises, optimization times. We characterize the trade-off between speed and accuracy towards real-time inference in applications.

A capsule is a group of neurons, whose activity vector represents the instantiation parameters of a specific type of entity. In this paper, we explore the capsule networks used for relation extraction in a multi-instance multi-label learning framework and propose a novel neural approach based on capsule networks with attention mechanisms. We evaluate our method with different benchmarks, and it is demonstrated that our method improves the precision of the predicted relations. Particularly, we show that capsule networks improve multiple entity pairs relation extraction.

E-commerce has become more popular with the growth in internet and network technologies. Many people feel convenient to buy products online using various forums such as Amazon, Flipchart, Awok etc. When customers buy the products online there is an option for them to provide their review comments. Many customers chose to provide their experience, opinion, feedback etc. Such product reviews are rich in information consisting of feedback shared by users.

A new generation of idols are singing and dancing in music videos in China, with plans to sell albums and perform in concerts where they will engage fans with personalised interaction. Only thing is, they don't actually exist, at least corporeally. In the latest Christmas music video released by Chinese girl idol group SNH48, six of the group's most popular stars sing and dance with some special partners – digital copies of themselves based on their looks, voices and body language. The four-minute music video, co-produced by Tencent-backed artificial intelligence (AI) start-up ObEN, claims to be the world's first commercially released song co-starring human singers and their AI 3D avatars. "This song is our first step to test the waters in the virtual idol market. We are planning to create more intelligent virtual idols, releasing albums and making movies for them," said Xiong Wei, vice-president of the Shanghai-based SNH48.

You are free to share this article under the Attribution 4.0 International license. Researchers have harnessed a powerful artificial intelligence platform to successfully treat a patient with advanced cancer, completely halting disease progression. The development represents a big step forward in personalized medicine, they say. In this clinical study, researchers gave a patient with metastatic castration-resistant prostate cancer (MCRPC) a novel drug combination consisting of the investigational drug ZEN-3694 and enzalutamide, an approved prostate cancer drug. The research team successfully used the platform, called CURATE.AI, to continuously identify the optimal doses of each drug to result in a durable response, allowing the patient to resume a completely normal and active lifestyle.

Photos of an artificial intelligence textbook for Chinese preschoolers have gone viral. Artificial Intelligence Experiment Materials is a 33-volume textbook series aimed at Chinese students from kindergarten to high school that was published this July by Henan People's Publishing House. AI researchers from Google, the Institute of Automation of the Chinese Academy of Sciences, and key Chinese universities collaborated on the textbooks, which pertain to an AI education initiative launched this July by the China Education Technology Association Smart Learning Committee and UNESCO. The aim is to democratize AI education in 100 Chinese schools, introduce pre-teens to the basics, strengthen teenagers' capability for using intelligent and applied technologies, and help train hundreds of new AI teachers. Also included in the initiative is a cloud-based AI e-learning platform that students can access via PC or WeChat.