Outfittery is an online personalized styling service targeted at men. We have hundreds of stylists who create thousands of bespoke outfits for our customers every day. A critical challenge faced by our stylists when creating these outfits is selecting an appropriate item of clothing that makes sense in the context of the outfit being created, otherwise known as style fit. Another significant challenge is knowing if the item is relevant to the customer based on their tastes, physical attributes and price sensitivity. At Outfittery we leverage machine learning extensively and combine it with human domain expertise to tackle these challenges. We do this by surfacing relevant items of clothing during the outfit building process based on what our stylist is doing and what the preferences of our customer are. In this paper we describe one way in which we help our stylists to tackle style fit for a particular item of clothing and its relevance to an outfit. A thorough qualitative and quantitative evaluation highlights the method's ability to recommend fashion items by style fit.

Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for localized image manipulations. We use face images as our example of choice. Depending on the image region, identity and other facial attributes can be modified. The proposed network can transfer parts of a face such as shape and color of eyes, hair, mouth, etc.~directly between persons while all other parts of the face remain unchanged. The network allows to generate modified images which appear like realistic images. Our model learns disentangled representations by weak supervision. We propose a localized resnet autoencoder optimized using several loss functions including a loss based on the semantic segmentation, which we interpret as masks, and a loss which enforces disentanglement by decomposition of the latent space into statistically independent subspaces. We evaluate the proposed solution w.r.t. disentanglement and generated image quality. Convincing results are demonstrated using the CelebA dataset.

Coarse correlation models strategic interactions of rational agents complemented by a correlation device, that is a mediator that can recommend behavior but not enforce it. Despite being a classical concept in the theory of normal-form games for more than forty years, not much is known about the merits of coarse correlation in extensive-form settings. In this paper, we consider two instantiations of the idea of coarse correlation in extensive-form games: normal-form coarse-correlated equilibrium (NFCCE), already defined in the literature, and extensive-form coarse-correlated equilibrium (EFCCE), which we introduce for the first time. We show that EFCCE is a subset of NFCCE and a superset of the related extensive-form correlated equilibrium. We also show that, in two-player extensive-form games, social-welfare-maximizing EFCCEs and NFCEEs are bilinear saddle points, and give new efficient algorithms for the special case of games with no chance moves. In our experiments, our proposed algorithm for NFCCE is two to four orders of magnitude faster than the prior state of the art.

We propose an iteration-free source separation algorithm based on Winner-Take-All (WTA) hash codes, which is a faster, yet accurate alternative to a complex machine learning model for single-channel source separation in a resource-constrained environment. We first generate random permutations with WTA hashing to encode the shape of the multidimensional audio spectrum to a reduced bitstring representation. A nearest neighbor search on the hash codes of an incoming noisy spectrum as the query string results in the closest matches among the hashed mixture spectra. Using the indices of the matching frames, we obtain the corresponding ideal binary mask vectors for denoising. Since both the training data and the search operation are bitwise, the procedure can be done efficiently in hardware implementations. Experimental results show that the WTA hash codes are discriminant and provide an affordable dictionary search mechanism that leads to a competent performance compared to a comprehensive model and oracle masking.

Embedding layer is commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. As the number of symbols increase, the number of embedding parameter, as well as their size, increase linearly and become problematically large. In this work, we aim to reduce the size of embedding layer via learning discrete codes and composing embedding vectors from the codes. More specifically, we propose a differentiable product quantization framework with two instantiations, which can serve as an efficient drop-in replacement for existing embedding layer. Empirically, we evaluate the proposed method on three different language tasks, and show that the proposed method enables end-to-end training of embedding compression that achieves significant compression ratios (14-238$\times$) at almost no performance cost (sometimes even better).

Huawei said on Friday it expects to lose $10 billion (£8bn) in revenues this year to sanctions imposed by the US in May, lower than an earlier estimate of $30bn. The company made the remarks as it unveiled a new AI chip and computing framework as part of broader efforts to phase out its reliance on technology made in the US. Huawei deputy chairman Eric Xu said the company was doing "much better" than initially feared, but that a sales "reduction of more than $10bn could happen". The company's revenues gained a boost from domestic sales, which surged by nearly one-third year-on-year in the June quarter. In May the US placed Huawei on a national security "entity list" that prevents US firms from trading with it, and while it has thus far imposed a series of delays that have prevented the sanctions from taking place, the uncertainty has led to a steep drop in Huawei's global sales.

In his writings, Gary Marcus is clear about two things: Artificial intelligence is an extremely promising technology that, if used in the right way, could significantly improve practices in health care and other industries. But right now, Marcus says, AI is getting off track, with potentially severe consequences for society and the field itself. That viewpoint makes Marcus -- a tech entrepreneur, author, and psychology professor at New York University -- a controversial figure in the world of artificial intelligence. He is among a few prominent scientists voicing skepticism about the dominance of deep learning, a type of AI architecture whose use has exploded in medicine and other fields. Unlock this article by subscribing to STAT Plus and enjoy your first 30 days free!

Motorists could soon enjoy quicker and easier getaways on bank holidays, as government announces plans today (26 August 2019) to open up data on planned changes to the road network, highlighting potential traffic jams up to months in advance. Tech firms could soon get access to this data thanks to a review of legislation around Traffic Regulation Orders (TROs) - the orders behind restrictions on the road network which allow for temporary roadworks or permanent changes to the road. Companies will potentially be able to develop and enhance navigational apps powered by AI, warning drivers up to months in advance of planned disruption to routes and offering alternatives to help save time and money. As a road user, there is nothing more frustrating than discovering roadworks and getting stuck in traffic jams. Today's announcement will help open up data, reducing congestion, pollution and frustration for road users.

Hotel cancellations can cause issues for many businesses in the industry. Not only is there the lost revenue as a result of the customer canceling, but this can also cause difficulty in coordinating bookings and adjusting revenue management practices. Data analytics can help to overcome this issue, in terms of identifying the customers who are most likely to cancel – allowing a hotel chain to adjust its marketing strategy accordingly. To investigate how machine learning can aid in this task, the ExtraTreesClassifer, logistic regression, and support vector machine models were employed in Python to determine whether cancellations can be accurately predicted with this model. For this example, both hotels are based in Portugal.

Automated recognition and talent management are on the list of the US Army's AI Task Force, as a result of its year-long collaboration with the Carnegie Mellon University on incorporating Artificial Intelligence (AI) into US Army systems. The task force's access to sensors, different types of electro-mechanical devices, and computing capabilities are enabling them to create AI for other applications as per the plan in the 2018 directive, which states, "The Army is establishing the Army-AI Task Force (A-AI TF) that will narrow an existing AI capability gap by leveraging current technological applications to enhance our warfighters, preserve peace, and, if required, fight to win." Five university staffers at National Robotics Engineering Center, an integral part of CMU's Robotics Institute, have formed an AI Hub to work directly with the Army task force. The task force is starting to fill gaps in its systems with AI. In March, the US Army invested US$72 million in a five-year AI fundamental research effort to research and discover capabilities for augmenting military personnel, optimizing operations, increasing readiness, and reducing casualties. According to the Combat Capabilities Development Command Army Research Laboratory, which is the US Army's corporate laboratory (ARL), in March, CMU will lead a consortium of multiple universities to work in collaboration with the Army lab to accelerate R&D of advanced algorithms, autonomy and AI to enhance national security and defense.