Sequential Recommendationdescribes a set of techniques to model dynamic user behavior in order to predict future interactions in sequential user data. At their core, such approaches model transition probabilities between items in a sequence, whether through Markov chains, recurrent networks, or more recently, Transformers. However both old and new issues remain, including data-sparsity and noisy data; such issues can impair the performance, especially in complex, parameter-hungry models. In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues. Contrastive SSL constructs augmentations from unlabelled instances, where agreements among positive pairs are maximized. It is challenging to devise a contrastive SSL framework for a sequential recommendation, due to its discrete nature, correlations among items, and skewness of length distributions. To this end, we propose a novel framework, Contrastive Self-supervised Learning for sequential Recommendation (CoSeRec). We introduce two informative augmentation operators leveraging item correlations to create high-quality views for contrastive learning. Experimental results on three real-world datasets demonstrate the effectiveness of the proposed method on improving model performance and the robustness against sparse and noisy data. Our implementation is available online at \url{https://github.com/YChen1993/CoSeRec}

"Art is the lie that enables us to realize the truth." - Pablo Picasso. For centuries, humans have dedicated themselves to producing arts to convey their imagination. The advancement in technology and deep learning in particular, has caught the attention of many researchers trying to investigate whether art generation is possible by computers and algorithms. Using generative adversarial networks (GANs), applications such as synthesizing photorealistic human faces and creating captions automatically from images were realized. This survey takes a comprehensive look at the recent works using GANs for generating visual arts, music, and literary text. A performance comparison and description of the various GAN architecture are also presented. Finally, some of the key challenges in art generation using GANs are highlighted along with recommendations for future work.

While image understanding on recognition-level has achieved remarkable advancements, reliable visual scene understanding requires comprehensive image understanding on recognition-level but also cognition-level, which calls for exploiting the multi-source information as well as learning different levels of understanding and extensive commonsense knowledge. In this paper, we propose a novel Cognitive Attention Network (CAN) for visual commonsense reasoning to achieve interpretable visual understanding. Specifically, we first introduce an image-text fusion module to fuse information from images and text collectively. Second, a novel inference module is designed to encode commonsense among image, query and response. Extensive experiments on large-scale Visual Commonsense Reasoning (VCR) benchmark dataset demonstrate the effectiveness of our approach. The implementation is publicly available at https://github.com/tanjatang/CAN

Loop-invariant synthesis is the basis of every program verification procedure. Due to its undecidability in general, a tool for invariant synthesis necessarily uses heuristics. Despite the common belief that the design of heuristics is vital for the effective performance of a verifier, little work has been performed toward obtaining the optimal heuristics for each invariant-synthesis tool. Instead, developers have hand-tuned the heuristics of tools. This study demonstrates that we can effectively and automatically learn a good heuristic via reinforcement learning for an invariant synthesizer PCSat. Our experiment shows that PCSat combined with the heuristic learned by reinforcement learning outperforms the state-of-the-art solvers for this task. To the best of our knowledge, this is the first work that investigates learning the heuristics of an invariant synthesis tool.

The development of machine learning and deep learning solutions typically follows a workflow that starts from the problem definition and goes through the crucial steps of collecting and exploring useful data, training and evaluating candidate models, deploying a solution, and finally documenting and maintaining the system once it is running in the wild (Figure 1). Despite its predictable structure, some steps of this process are iterative by nature and usually require multiple rounds of adjustments, fine-tuning, and optimizations. In this blog post we look at the process of running multiple machine learning experiments while searching for the best solution for a given problem and discuss the need to document the process in a structured way. We will discuss the Why, What and How of managing experiments and then we'll walk through an example of what this looks like in a real-world example. Machine learning (ML) and deep learning (DL) involve a fair amount of "trial and error" regardless of the task (regression, classification, prediction, segmentation), choice of model architecture, and size or complexity of the associated data set.

A deep learning score accurately predicted PD-L1 expression among a cohort of patients with non-small cell lung cancer who underwent PET/CT scans, according to study findings published in Journal for ImmunoTherapy of Cancer. "This study is important, as it is the single largest multi-institutional radiomic study population of [patients with NSCLC] to date treated with immunotherapy who had PET/CT scans that were used to predict PD-L1 status and subsequent treatment response," Robert J. Gillies, PhD, chair of cancer physiology and vice chair of radiology research at Moffitt Cancer Center, said in a press release. "Because images are routinely obtained and are not subject to sampling bias per se, we propose that the individualized risk assessment information provided by these analyses may be useful as a future clinical decision support tool pending larger prospective trials." Gillies and colleagues developed a deep learning score to predict PD-L1 expression, durable clinical benefit, PFS and OS among 697 patients with NSCLC treated with immune checkpoint inhibitors across three institutions. According to study results, the score enabled researchers to distinguish between patients with PD-L1-positive and PD-L1-negative status.

Are you a researcher or a startupper with a super cool deep learning system you want to deploy to save the world? Well, you probably can’t…

Houston-based ThirdAI, a company building tools to speed up deep learning technology without the need for specialized hardware like graphics processing units, brought in $6 million in seed funding. Neotribe Ventures, Cervin Ventures and Firebolt Ventures co-led the investment, which will be used to hire additional employees and invest in computing resources, Anshumali Shrivastava, Third AI co-founder and CEO, told TechCrunch. Shrivastava, who has a mathematics background, was always interested in artificial intelligence and machine learning, especially rethinking how AI could be developed in a more efficient manner. It was when he was at Rice University that he looked into how to make that work for deep learning. He started ThirdAI in April with some Rice graduate students. ThirdAI's technology is designed to be "a smarter approach to deep learning," using its algorithm and software innovations to make general-purpose central processing units (CPU) faster than graphics processing units for training large neural networks, Shrivastava said.

The definition of creativity proposed by Marget Boden says it is the ability to come up with ideas or artifacts that are new, surprising, and valuable. And so far some of the current systems in artificial intelligence can satisfy this simplified description. To understand this process more deeply, the science community introduced three types of creativity. It is an unfamiliar connections of already existed ideas. This process can be compared to averaging over the training samples, and generating something new(orange dot) which still falls into the space that examples cover(green dotted line).

OpenAI has released a new version of Codex, an AI system that translates written language into code. The company unveiled the upgraded software on Tuesday. It looks like a seriously powerful programming tool -- and a slightly scary one. In a live demo, OpenAI used the system to convert written English commands into simple games and websites. Attend the tech festival of the year and get your super early bird ticket now!