For VR environments to be fully immersive, we must strive towards graphics that can mirror reality. Unfortunately, such high-level graphics are difficult to attain in real-time without running into problems with framerate and stuttering gameplay, which breaks immersion and can cause motion sickness in players. The consequence of this is that the majority of VR experiences must use simplistic graphics to keep the experience as smooth as possible. Fortunately, computer graphics titans Nvidia have been utilising deep learning techniques to make such dreams possible. "Deep Learning Super Sampling" is a technology developed by Nvidia which allows high-resolution images to be generated for a low-res image input, allowing for high-quality graphics for VR to be less costly than before.

The resurgence of artificial intelligence (AI) is largely due to advances in pattern-recognition due to deep learning, a form of machine learning that does not require explicit hard-coding. The architecture of deep neural networks is somewhat inspired by the biological brain and neuroscience. Like the biological brain, the inner workings of exactly why deep networks work are largely unexplained, and there is no single unifying theory. Recently researchers at the Massachusetts Institute of Technology (MIT) revealed new insights about how deep learning networks work to help further demystify the black box of AI machine learning. The MIT research trio of Tomaso Poggio, Andrzej Banburski, and Quianli Liao at the Center for Brains, Minds, and Machines developed a new theory as to why deep networks work and published their study published on June 9, 2020 in PNAS (Proceedings of the National Academy of Sciences of the United States of America).

Recently, Facebook announced the availability of the latest version of PyTorch, PyTorch 1.6. The social media giant also made a massive announcement that Microsoft has expanded its participation in the PyTorch community and is taking ownership of the development and maintenance of the PyTorch to build for Windows. PyTorch is one of the most popular machine learning libraries in Python. The version 1.6 release includes several new APIs, tools for performance improvement and profiling, as well as significant updates to both distributed data-parallel (DDP) and remote procedure call (RPC) based distributed training. According to the blog post, from this release onward, features will be classified as Stable, Beta and Prototype, where Prototype features are not included as part of the binary distribution and are instead available through either building from source, using nightlies or via a compiler flag. Automatic mixed precision (AMP) training is now natively supported and is a stable feature.

Humans can easily reason about the sequence of high level actions needed to complete tasks, but it is particularly difficult to instil this ability in robots trained from relatively few examples. This work considers the task of neural action sequencing conditioned on a single reference visual state. This task is extremely challenging as it is not only subject to the significant combinatorial complexity that arises from large action sets, but also requires a model that can perform some form of symbol grounding, mapping high dimensional input data to actions, while reasoning about action relationships. Drawing on human cognitive abilities to rearrange objects in scenes to create new configurations, we take a permutation perspective and argue that action sequencing benefits from the ability to reason about both permutations and ordering concepts. Empirical analysis shows that neural models trained with latent permutations outperform standard neural architectures in constrained action sequencing tasks. Results also show that action sequencing using visual permutations is an effective mechanism to initialise and speed up traditional planning techniques and successfully scales to far greater action set sizes than models considered previously.

Natural language interfaces to databases (NLIDB) democratize end user access to relational data. Due to fundamental differences between natural language communication and programming, it is common for end users to issue questions that are ambiguous to the system or fall outside the semantic scope of its underlying query language. We present Photon, a robust, modular, cross-domain NLIDB that can flag natural language input to which a SQL mapping cannot be immediately determined. Photon consists of a strong neural semantic parser (63.2\% structure accuracy on the Spider dev benchmark), a human-in-the-loop question corrector, a SQL executor and a response generator. The question corrector is a discriminative neural sequence editor which detects confusion span(s) in the input question and suggests rephrasing until a translatable input is given by the user or a maximum number of iterations are conducted. Experiments on simulated data show that the proposed method effectively improves the robustness of text-to-SQL system against untranslatable user input. The live demo of our system is available at http://naturalsql.com.

It is not surprise for machine learning models to provide decent prediction accuracy of soccer games outcomes based on various objective metrics. However, the performance is not that decent in terms of predicting difficult and valuable matches. A deep learning model is designed and trained on a real sequential trading data from the real prediction market, with the assumption that such trading data contain critical latent information to determine the game outcomes. A new loss function is proposed which biases the selection toward matches with high investment return to train our model. Full investigation of 4669 top soccer league matches showed that our model traded off prediction accuracy for high value return due to a certain ability to detect dark horses. A further try is conducted to depict some indicators discovered by our model for describing key features of big dark horses and regular hot horses.

In this paper, we present SemEval-2020 Task 4, Commonsense Validation and Explanation (ComVE), which includes three subtasks, aiming to evaluate whether a system can distinguish a natural language statement that makes sense to humans from one that does not, and provide the reasons. Specifically, in our first subtask, the participating systems are required to choose from two natural language statements of similar wording the one that makes sense and the one does not. The second subtask additionally asks a system to select the key reason from three options why a given statement does not make sense. In the third subtask, a participating system needs to generate the reason. We finally attracted 39 teams participating at least one of the three subtasks. For Subtask A and Subtask B, the performances of top-ranked systems are close to that of humans. However, for Subtask C, there is still a relatively large gap between systems and human performance.

This paper presents the Jazz Transformer, a generative model that utilizes a neural sequence model called the Transformer-XL for modeling lead sheets of Jazz music. Moreover, the model endeavors to incorporate structural events present in the Weimar Jazz Database (WJazzD) for inducing structures in the generated music. While we are able to reduce the training loss to a low value, our listening test suggests however a clear gap between the average ratings of the generated and real compositions. We therefore go one step further and conduct a series of computational analysis of the generated compositions from different perspectives. This includes analyzing the statistics of the pitch class, grooving, and chord progression, assessing the structureness of the music with the help of the fitness scape plot, and evaluating the model's understanding of Jazz music through a MIREX-like continuation prediction task. Our work presents in an analytical manner why machine-generated music to date still falls short of the artwork of humanity, and sets some goals for future work on automatic composition to further pursue.

Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias. This causes a newly trained model to act greedily and favor items that have already been engaged by users. This behavior is particularly harmful in personalised ads recommendations, as it can also cause new campaigns to remain unexplored. Exploration aims to address this limitation by providing new information about the environment, which encompasses user preference, and can lead to higher long-term reward. In this work, we formulate a display advertising recommender as a contextual bandit and implement exploration techniques that require sampling from the posterior distribution of click-through-rates in a computationally tractable manner. Traditional large-scale deep learning models do not provide uncertainty estimates by default. We approximate these uncertainty measurements of the predictions by employing a bootstrapped model with multiple heads and dropout units. We benchmark a number of different models in an offline simulation environment using a publicly available dataset of user-ads engagements. We test our proposed deep Bayesian bandits algorithm in the offline simulation and online AB setting with large-scale production traffic, where we demonstrate a positive gain of our exploration model.

Artificial intelligence (AI) has a long tradition. The name AI was coined by McCarthy at the Dartmouth conference in 1956 starting a concerted endeavor that continues to date [1]. The initial focus of AI was on symbolic models and reasoning as search followed by the first wave of neural networks and expert systems [2-4]. In the 1980s neural networks had a first return by invention of the back-propagation algorithm [5] and in the 1990s research about intelligent agents received broad interest. Recently, big data became available and led to revival of neural networks in the form of deep neural networks [6, 7]. AI has achieved great successes in many different fields including robotics, speech recognition, facial recognition, healthcare and finance [7-12]. Given the breath of AI applications and the variety of methods used it is no surprise that seemingly simple questions, e.g., regarding the aims and goals of AI got obscured especially for those scientists who did not accompany the field since