Medical data analytics startup Healx raised $56M from Atomico and others. Standard Cognition patented an inventory management system. Here's what went down in artificial intelligence this week. Become a CB Insights customer. If you're already a customer, log in here.

Word embedding -- the mapping of words into numerical vector spaces -- has proved to be an incredibly important method for natural language processing (NLP) tasks in recent years, enabling various machine learning models that rely on vector representation as input to enjoy richer representations of text input. These representations preserve more semantic and syntactic information on words, leading to improved performance in almost every imaginable NLP task. Both the novel idea itself and its tremendous impact have led researchers to consider the problem of how to provide this boon of richer vector representations to larger units of texts -- from sentences to books. This effort has resulted in a slew of new methods to produce these mappings, with various innovative solutions to the problem and some notable breakthroughs. This post is meant to present the different ways practitioners have come up with to produce document embeddings. Note: I use the word document here to refer to any sequence of words, ranging from sentences and paragraphs through social media posts all way up to articles, books and more complexly structured text documents (e.g. In this post, I will touch upon not only approaches that are direct extensions of word embedding techniques (e.g., in the way doc2vec extends word2vec), but also other notable techniques that produce -- sometimes among other outputs -- a mapping of documents to vectors in ℝⁿ. I will also try to provide links and references to both the original papers and code implementations of the reviewed methods whenever possible. Note: This topic is somewhat related, but not equivalent, to the problem of learning structured text representations (e.g., Liu & Lapata, 2018). The ability to map documents to informative vector representations has a wide range of applications.

Deep learning also uses deduction, but in a linear, basic, and one-dimensional way. Training the artificial neural networks to classify lions as dangerous might make them sensitive only to lions. A bear can't get classified as dangerous automatically. Training them to identify a cat will only make them recognize a cat, but not deduce that a leopard belongs to the cat family. Similarly, through facial recognition, deep learning can tag faces on photos but might stumble when there are faces of siamese twins.

The University of Toronto and the affiliated Vector Institute for Artificial Intelligence have announced the recruitment of two rising stars in machine learning research as part of a continued drive to assemble the best AI talent in the world. Chris Maddison and Jakob Foerster will both come to U of T having completed their doctoral research at the University of Oxford. He earned his undergraduate and master's degrees in computer science at U of T – the latter under the supervision of University Professor Emeritus Geoffrey Hinton. A senior research scientist at Google-owned AI firm DeepMind, Maddison will join U of T's departments of computer science and statistical sciences in the Faculty of Arts & Science as an assistant professor next summer. Foerster, a research scientist at Facebook AI Research, will start as an assistant professor in the department of computer and mathematical sciences at U of T Scarborough in fall of 2020.

Researchers from all over the world contribute to this repository as a prelude to the peer review process for publication in traditional journals. We hope to save you some time by picking out articles that represent the most promise for the typical data scientist. The articles listed below represent a fraction of all articles appearing on the preprint server. They are listed in no particular order with a link to each paper along with a brief overview. Especially relevant articles are marked with a "thumbs up" icon.

Cognex CGNX recently announced the acquisition of Seoul-based SUALAB, a developer of deep learning-based vision software. Although the financial terms of the acquisition have been kept under wraps, per a Pulse article the transaction price is estimated to be $168.6 million. Deep learning allows Cognex to solve the most complex vision application operations in factories faster, easier and in a cost-effective manner. The addition of SUALAB's Intellectual property and highly skillful engineering team, which specializes in deep learning, is expected to strengthen the company's product portfolio. The latest acquisition will help Cognex to reap benefits from strong prospects of the global deep learning system software market.

The latest market analysis report on the Deep Learning market performs industry diagnostic as a way to accumulate valuable data into the business environment of the Deep Learning market for the forecast period 2019 – 2026. The subject matter experts behind the research have collected vital statistics on the market share, size and growth as a way to help stakeholders, business owners and field marketing personnel identify the areas to reduce costs, improve sales, explore new opportunities and streamline their processes. Unbiased perspective on intangible aspects such as key challenges, threats, new entrants as well as strengths and weaknesses of the prominent vendors too are discussed in this market intelligence report. By offering expert assistance, it would be able to assist humans in extending their capabilities. Organizations are using deep learning networks to get valuable insights from huge amount of data.

Likelihood from a generative model is a natural statistic for detecting out-of-distribution (OoD) samples. However, generative models have been shown to assign higher likelihood to OoD samples compared to ones from the training distribution, preventing simple threshold-based detection rules. We demonstrate that OoD detection fails even when using more sophisticated statistics based on the likelihoods of individual samples. To address these issues, we propose a new method that leverages batch normalization. We argue that batch normalization for generative models challenges the traditional i.i.d. data assumption and changes the corresponding maximum likelihood objective. Based on this insight, we propose to exploit in-batch dependencies for OoD detection. Empirical results suggest that this leads to more robust detection for high-dimensional images.

We present an optimal transport (OT) framework for generalized zero-shot learning (GZSL) of imaging data, seeking to distinguish samples for both seen and unseen classes, with the help of auxiliary attributes. The discrepancy between features and attributes is minimized by solving an optimal transport problem. {Specifically, we build a conditional generative model to generate features from seen-class attributes, and establish an optimal transport between the distribution of the generated features and that of the real features.} The generative model and the optimal transport are optimized iteratively with an attribute-based regularizer, that further enhances the discriminative power of the generated features. A classifier is learned based on the features generated for both the seen and unseen classes. In addition to generalized zero-shot learning, our framework is also applicable to standard and transductive ZSL problems. Experiments show that our optimal transport-based method outperforms state-of-the-art methods on several benchmark datasets.

We propose a novel learning framework for recommendation systems, assisting collaborative filtering with a synthetic feedback loop. The proposed framework consists of a "recommender" and a "virtual user." The recommender is formulizd as a collaborative-filtering method, recommending items according to observed user behavior. The virtual user estimates rewards from the recommended items and generates the influence of the rewards on observed user behavior. The recommender connected with the virtual user constructs a closed loop, that recommends users with items and imitates the unobserved feedback of the users to the recommended items. The synthetic feedback is used to augment observed user behavior and improve recommendation results. Such a model can be interpreted as the inverse reinforcement learning, which can be learned effectively via rollout (simulation). Experimental results show that the proposed framework is able to boost the performance of existing collaborative filtering methods on multiple datasets.