We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedding extractor. Cosine similarity is an effective metric for speaker verification in this embedding space. We also address the problem of choosing an architecture for the extractor. We found that deep networks with residual frame level connections outperform wide but relatively shallow architectures. This paper also proposes several improvements for previous DNN-based extractor systems to increase the speaker recognition accuracy. We show that the discriminatively trained similarity metric learning approach outperforms the standard LDA-PLDA method as an embedding backend. The results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate robustness of the proposed systems when dealing with close to real-life conditions.

Deep learning searches for nonlinear factors for predicting asset returns. Predictability is achieved via multiple layers of composite factors as opposed to additive ones. Viewed in this way, asset pricing studies can be revisited using multi-layer deep learners, such as rectified linear units (ReLU) or long-short-term-memory (LSTM) for time-series effects. State-of-the-art algorithms including stochastic gradient descent (SGD), TensorFlow and dropout design provide imple- mentation and efficient factor exploration. To illustrate our methodology, we revisit the equity market risk premium dataset of Welch and Goyal (2008). We find the existence of nonlinear factors which explain predictability of returns, in particular at the extremes of the characteristic space. Finally, we conclude with directions for future research.

Autonomous Learning for Robotics aims to endow (robotic) agents with the capability to learn from and act in their environment, so that it can adapt to previously unseen situations. In order to be able to learn from this interaction, an agent has to build compact representations of the environments, using information captured from a high dimensional raw input. Current approaches favor the learning of representations using Deep Neural Networks ([1], [2], [3]). Supervised learning extracts representations from the data to solve a classification task, providing the agent with hierarchical compact representations of different sensory streams ([4], [5]). However, these state-of-the-art machine learning algorithms are not suitable for autonomous learning, as they rely on labeled data, which are costly to acquire, and are constraining the representations on the classes they were trained on. Unsupervised learning allows to learn hierarchical compression for different data streams ([6], [7], [8]).

This paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair. This task can be considered a low-resourced task from the point of view of the domain and the language pair. To face this task, this paper reports experiments on a cascade pivot strategy through Spanish for the neural machine translation using the English-Spanish SCIELO and Spanish-Catalan El Peri\'odico database. To test the final performance of the system, we have created a new test data set for English-Catalan in the biomedical domain which is freely available on request.

Recent advances in artificial intelligence (AI) and machine learning have created a general perception that AI could be used to solve complex problems, and in some situations over-hyped as a tool that can be so easily used. Unfortunately, the barrier to realization of mass adoption of AI on various business domains is too high because most domain experts have no background in AI. Developing AI applications involves multiple phases, namely data preparation, application modeling, and product deployment. The effort of AI research has been spent mostly on new AI models (in the model training stage) to improve the performance of benchmark tasks such as image recognition. Many other factors such as usability, efficiency and security of AI have not been well addressed, and therefore form a barrier to democratizing AI. Further, for many real world applications such as healthcare and autonomous driving, learning via huge amounts of possibility exploration is not feasible since humans are involved. In many complex applications such as healthcare, subject matter experts (e.g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results. In this paper, we take a new perspective on developing AI solutions, and present a solution for making AI usable. We hope that this resolution will enable all subject matter experts (eg. Clinicians) to exploit AI like data scientists.

We propose a novel machine-learning framework for dialogue modeling which uses representations based on hash functions. More specifically, each person's response is represented by a binary hashcode where each bit reflects presence or absence of a certain text pattern in the response. Hashcodes serve as compressed text representations, allowing for efficient similarity search. Moreover, hashcode of one person's response can be used as a feature vector for predicting the hashcode representing another person's response. The proposed hashing model of dialogue is obtained by maximizing a novel lower bound on the mutual information between the hashcodes of consecutive responses. We apply our approach in psychotherapy domain, evaluating its effectiveness on a real-life dataset consisting of therapy sessions with patients suffering from depression.

Recent years have seen deep neural networks (DNNs) becoming wider and deeper to achieve better performance in many applications of AI. Such DNNs however require huge amounts of memory to store weights and intermediate results (e.g., activations, feature maps, etc.) in propagation. This requirement makes it difficult to run the DNNs on devices with limited, hard-to-extend memory, degrades the running time performance, and restricts the design of network models. We address this challenge by developing a novel profile-guided memory optimization to efficiently and quickly allocate memory blocks during the propagation in DNNs. The optimization utilizes a simple and fast heuristic algorithm based on the two-dimensional rectangle packing problem. Experimenting with well-known neural network models, we confirm that our method not only reduces the memory consumption by up to $49.5\%$ but also accelerates training and inference by up to a factor of four thanks to the rapidity of the memory allocation and the ability to use larger mini-batch sizes.

A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from single passages independently. But some questions require a combination of evidence from across different sources to answer correctly. In this paper, we propose two models which make use of multiple passages to generate their answers. Both use an answer-reranking approach which reorders the answer candidates generated by an existing state-of-the-art QA model. We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer. Our models have achieved state-of-the-art results on three public open-domain QA datasets: Quasar-T, SearchQA and the open-domain version of TriviaQA, with about 8 percentage points of improvement over the former two datasets.

Editor's Note: This piece was written by Gary Newgaard, Vice President, Public Sector at Pure Storage. The opinions represented in this piece are independent of Smart Cities Dive's views. Ask average citizens about their biggest frustrations in dealing with government organizations and you're likely to conjure up at least a few stories of never-ending lines at the Department of Motor Vehicles (DMV). Bureaucracy and manual processes have, fairly or not, become synonymous with the business of government. They upset constituents, and chances are they don't help government workers get their jobs done, either.

Photoshop could become a thing of the past thanks to new technology that can touch-up badly damaged photos. The Nvidia software uses AI and deep-learning algorithms to predict what a missing portion of a picture should look like and recreate it with incredible accuracy. All users need to do is click and drag over the area to be filled in and the image is instantly updated. As well as restoring old physical photos that have been damaged, the technique could also be used to fix corrupted pixels or bad edits made to digital files. Graphics specialist Nvidia, based in Santa Clara, California trained its neural network using a variety of irregular shaped holes in images.