The push by enterprises for explainable artificial intelligence is shining a light on one of the problematic aspects of machine learning models. That is, if the models operate in so-called black boxes, they don't give a business visibility into why they've arrived at the recommendations they do. But, according to experts, the enterprise demand for explainable artificial intelligence overlooks a number of characteristics about current applications of AI, including the fact that not all machine learning models require the same level of interpretability. "The importance of interpretability really depends on the downstream application," said Zoubin Ghahramani, professor of information engineering at the University of Cambridge and chief scientist at Uber Technologies Inc., during a press conference at the recent Artificial Intelligence Conference hosted by O'Reilly Media and Intel AI. A machine learning model that automatically captions an image would not need to be held to the same standards as machine learning models that determine how loans should be distributed, he contended.

Published online 30 May 2017 [31] Perez JC (2017) The "Master Code of DNA": Towards the Discovery of the SNPs Function (Single-Nucleotide Polymorphism).

Drones are a controversial tech gadget to say the least. They can pose a risk to aircraft, cause potential privacy issues, and are being used to smuggle contraband into prisons. Despite their bad reputation, a lot of research is being put into the use of unmanned aerial vehicles (UAVs) within emergency missions. At New York University's Abu Dhabi campus, Professor of Electrical and Computer Engineering, Antonios Tzes, has been manning a project across five different universities in the US, Sweden, Switzerland, Netherlands, and Greece, to develop drones for use inside buildings, particularly in fire situations. After designing ground vehicles for rescue operations, Tzes and his team were looking for a way to move away from the ground. "We needed to go up into the air, in confined spaces, and drones were the logical way to do it," he tells the Standard.

Somewhere within the Vatican exists the Vatican Secret Archives, whose 53 miles of shelving contains more than 600 collections of account books, official acts, papal correspondence, and other historical documents. Though its holdings date back to the eighth century, it has in the past few weeks come to worldwide attention. This has brought about all manner of jokes about the plot of Dan Brown's next novel, but also important news about the technology of manuscript digitization. It seems a project to get the contents of the Vatican Secret Archives digitized and online has made great progress cracking a problem that once seemed impossibly difficult: turning handwriting into computer-searchable text. In Codice Ratio is "developing a full-fledged system to automatically transcribe the contents of the manuscripts" that uses not the standard method of optical character recognition (OCR), which looks for the spaces between words, but a new way that can handle connected cursive and calligraphic letters.

In the era of "big data", it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what's really going on in the data. For example, it is often of interest to know which, if any, of the predictors in a fitted model are relatively influential on the predicted outcome. Some modern algorithms---like random forests and gradient boosted decision trees---have a natural way of quantifying the importance or relative influence of each feature. Other algorithms---like naive Bayes classifiers and support vector machines---are not capable of doing so and model-free approaches are generally used to measure each predictor's importance. In this paper, we propose a standardized, model-based approach to measuring predictor importance across the growing spectrum of supervised learning algorithms. Our proposed method is illustrated through both simulated and real data examples. The R code to reproduce all of the figures in this paper is available in the supplementary materials.

Knowledge distillation (KD) consists of transferring knowledge from one machine learning model (the teacher}) to another (the student). Commonly, the teacher is a high-capacity model with formidable performance, while the student is more compact. By transferring knowledge, one hopes to benefit from the student's compactness. %we desire a compact model with performance close to the teacher's. We study KD from a new perspective: rather than compressing models, we train students parameterized identically to their teachers. Surprisingly, these {Born-Again Networks (BANs), outperform their teachers significantly, both on computer vision and language modeling tasks. Our experiments with BANs based on DenseNets demonstrate state-of-the-art performance on the CIFAR-10 (3.5%) and CIFAR-100 (15.5%) datasets, by validation error. Additional experiments explore two distillation objectives: (i) Confidence-Weighted by Teacher Max (CWTM) and (ii) Dark Knowledge with Permuted Predictions (DKPP). Both methods elucidate the essential components of KD, demonstrating a role of the teacher outputs on both predicted and non-predicted classes. We present experiments with students of various capacities, focusing on the under-explored case where students overpower teachers. Our experiments show significant advantages from transferring knowledge between DenseNets and ResNets in either direction.

With the increase of machine learning usage by industries and scientific communities in a variety of tasks such as text mining, image recognition and self-driving cars, automatic setting of hyper-parameter in learning algorithms is a key factor for achieving satisfactory performance regardless of user expertise in the inner workings of the techniques and methodologies. In particular, for a reinforcement learning algorithm, the efficiency of an agent learning a control policy in an uncertain environment is heavily dependent on the hyper-parameters used to balance exploration with exploitation. In this work, an autonomous learning framework that integrates Bayesian optimization with Gaussian process regression to optimize the hyper-parameters of a reinforcement learning algorithm, is proposed. Also, a bandits-based approach to achieve a balance between computational costs and decreasing uncertainty about the Q-values, is presented. A gridworld example is used to highlight how hyper-parameter configurations of a learning algorithm (SARSA) are iteratively improved based on two performance functions.

ABSTRACT We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no longer organized in a waterfall scheme. The whole system is realized by traversing backtrack arrows and cycles between various stages. In order to give a compact and effective representation of the features, the standard early temporal integration is combined with other selection and extraction phases: on the one hand, the selection of the most meaningful characteristics based on information gain, and on the other hand, the inclusion of the nonlinear correlation between this subset of features, determined by an autoencoder. The results of the experiments conducted on GTZAN dataset reveal a noticeable contribution of this methodology towards the model's performance in classification task. Index Terms-- Musical signal, genre classification, feature extraction and selection, information gain, autoencoder 1. INTRODUCTION One of the current subjects of research in Computer Science and Engineering concerns the enhancement of machines with abilities which are related to the human perception of the environment.

There are many important regression problems in real-world brain-computer interface (BCI) applications, e.g., driver drowsiness estimation from EEG signals. This paper considers offline analysis: given a pool of unlabeled EEG epochs recorded during driving, how do we optimally select a small number of them to label so that an accurate regression model can be built from them to label the rest? Active learning is a promising solution to this problem, but interestingly, to our best knowledge, it has not been used for regression problems in BCI so far. This paper proposes a novel enhanced batch-mode active learning (EBMAL) approach for regression, which improves upon a baseline active learning algorithm by increasing the reliability, representativeness and diversity of the selected samples to achieve better regression performance. We validate its effectiveness using driver drowsiness estimation from EEG signals. However, EBMAL is a general approach that can also be applied to many other offline regression problems beyond BCI.

Active learning (AL) [33], a subfield of machine learning, considers the following problem: if the learning algorithm can choose the training data, then which training samples should it choose to maximize the learning performance, under a fixed budget, e.g., the maximum number of labeled training samples? As an example, consider emotion estimation in affective computing [28]. Emotions can be represented as continuous numbers in the 2D space of arousal and valence [30], or in the 3D space of arousal, valence, and dominance [26]. However, emotions are very subjective, subtle, and uncertain. So, usually multiple human assessors are needed to obtain the groundtruth emotion values for each affective sample (video, audio, image, physiological signal, etc). For example, 14-16 assessors were used to evaluate each video clip in the DEAP dataset [21], six to 17 assessors for each utterance in the VAM (Vera am Mittag in German, Vera at Noon in English) spontaneous speech corpus [16], and at least 110 assessors for each sound in the IADS-2 (International Affective Digitized Sounds 2nd Edition) dataset [4]. This is very time-consuming and labor-intensive. How should we optimally select the affective samples to label so that an accurate regression model can be built with the minimum cost (i.e., the minimum number of labeled samples)?