The way you walk says a lot about how you're feeling at any given moment. When you're downtrodden or depressed, for example, you're more likely to slump your shoulders than when you're contented or upset. Leveraging this somatic lexicon, researchers at the University of Chapel Hill and the University of Maryland recently investigated a machine learning method that can identify a person's perceived emotion, valence (e.g., negative or positive), and arousal (calm or energetic) from their gait alone. The researchers claim this approach -- which they believe is the first of its kind -- achieved 80.07% percent accuracy in preliminary experiments. "Emotions play a large role in our lives, defining our experiences and shaping how we view the world and interact with other humans," wrote the coauthors.

Big artificial intelligence companies are promising an automated future but many of their products rely on the labeled training data coming from Scale AI, a startup that highlights machine learning's intimate bond between human contractors and algorithms. The three-year-old startup announced Monday that it had closed a $100 million Series C round of financing led by Founders Fund with participation from Accel, Coatue Management, Index Ventures, Spark Capital, Thrive Capital, Instagram founders Kevin Systrom and Mike Krieger and Quora CEO Adam d'Angelo. A report in Bloomberg details that this funding will bring Scale's valuation past $1 billion. "In general, AI and machine learning is just growing so quickly as a field, that it's appropriate to raise this amount that will allow us to capitalize on our ambitions," the company's 22-year-old executive Alexandr Wang told TechCrunch in an interview. "We don't want to be in the business of constantly needing to raise capital, so ideally this is the last fundraise for us."

I started 2019 by saying it would be the year of AI. As we witness how this game-changing technology is dominating the agendas of leading organisations and nations, I can say I was right. At Microsoft, we have helped organisations in Thailand harness artificial intelligence as the core of their digital transformation strategy, offering them a competitive advantage. Whether employed to improve operational efficiency or create entirely new business models, making AI part of your core strategy translates into growth and added value. To help understand how AI is shaping the future for Thai businesses, Microsoft partnered with the research firm IDC to survey readiness for AI adoption among business leaders and workers.

Artificial intelligence (AI) researchers are unable to explain exactly how deep learning algorithms arrive at their conclusions. Deep learning is complex by nature, but that does not excuse the pursuit of seeking clarity and understanding of black-box decision making. The quality of a machine learning algorithm requires some level of transparency and an understanding of how a decision was made--this impacts the generalizability of the algorithm and the reliability of the output. Recently in March 2019, researchers from the Fraunhofer Heinrich Hertz Institute, Technische Universität Berlin, Singapore University of Technology and Design, Korea University, and Max Planck Institut für Informatik, published in Nature Communications a method of validating the behavior of nonlinear machine learning in order to better assess the quality of the learning system. The research team of Klaus-Robert Müller, Wojciech Samek, Grégoire Montavon, Alexander Binder, Stephan Wäldchen, and Sebastian Lapuschkin discovered that various AI systems using what psychologists would characterize as a "Clever Hans" type of decision-based on correlation.

Amazon has given Alexa users the option to disable human review of their voice recordings, and committed to greater clarity about its use of the strategy in future, but says it will not follow Google and Apple in halting the practice altogether in Europe. Echo owners, and other users of the company's virtual voice assistant, can turn off human review in the Alexa privacy page by disabling a setting labelled "help improve Amazon services and develop new features". A company spokesperson said: "We take customer privacy seriously and continuously review our practices and procedures. For Alexa, we already offer customers the ability to opt out of having their voice recordings used to help develop new Alexa features. "The voice recordings from customers who use this opt-out are also excluded from our supervised learning workflows that involve manual review of an extremely small sample of Alexa requests.

If you were going to lose your job, would you prefer to be replaced by a robot or another person? If you said robot, you're in the majority. Most people would prefer a robot to take their job if they had to lose it, but they would prefer to see another human step in if a co-worker was going to lose theirs. "Being replaced by modern technology versus being replaced by humans has different psychological consequences," says Armin Granulo at Technical University of Munich in Germany. He and his colleagues set out to examine these differences.

Classifying limb movements using brain activity is an important task in Brain-computer Interfaces (BCI) that has been successfully used in multiple application domains, ranging from human-computer interaction to medical and biomedical applications. This paper proposes a novel solution for classification of left/right hand movement by exploiting a Long Short-Term Memory (LSTM) network with attention mechanism to learn from sequential data available in the electroencephalogram (EEG) signals. In this context, a wide range of time and frequency domain features are first extracted from the EEG signal and are then evaluated using a Random Forest (RF) to select the most important features. The selected features are arranged as a spatio-temporal sequence to feed the LSTM network, learning from the sequential data to perform the classification task. We conduct extensive experiments with the EEG motor movement/imagery database and show that our proposed solution achieves effective results outperforming baseline methods and the state-of-the-art in both intra-subject and cross-subject evaluation schemes. Moreover, we utilize the proposed framework to analyze the information as received by the sensors and monitor the activated regions of the brain by tracking EEG topography throughout the experiments.

Facial analysis permits many investigations some of the most important of which are craniofacial identification, facial recognition, and age and sex estimation. In forensics, photo-anthropometry describes the study of facial growth and allows the identification of patterns in facial skull development by using a group of cephalometric landmarks to estimate anthropological information. In several areas, automation of manual procedures has achieved advantages over and similar measurement confidence as a forensic expert. This manuscript presents an approach using photo-anthropometric indexes, generated from frontal faces cephalometric landmarks, to create an artificial neural network classifier that allows the estimation of anthropological information, in this specific case age and sex. The work is focused on four tasks: i) sex estimation over ages from 5 to 22 years old, evaluating the interference of age on sex estimation; ii) age estimation from photo-anthropometric indexes for four age intervals (1 year, 2 years, 4 years and 5 years); iii) age group estimation for thresholds of over 14 and over 18 years old; and; iv) the provision of a new data set, available for academic purposes only, with a large and complete set of facial photo-anthropometric points marked and checked by forensic experts, measured from over 18,000 faces of individuals from Brazil over the last 4 years. The proposed classifier obtained significant results, using this new data set, for the sex estimation of individuals over 14 years old, achieving accuracy values greater than 0.85 by the F_1 measure. For age estimation, the accuracy results are 0.72 for measure with an age interval of 5 years. For the age group estimation, the measures of accuracy are greater than 0.93 and 0.83 for thresholds of 14 and 18 years, respectively.

Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of the model can be a time-consuming process of trial and error. While a small network with few neurons might not be able to capture the intricacies of a given task, having too many neurons can lead to overfitting and poor generalization. Here, we propose a practical method that employs matrix conditioning to automatically design the structure of layers of a feed-forward network, by first adjusting the proportion of neurons among the layers of a network and then scaling the size of network up or down. Results on sample image and non-image datasets demonstrate that our method results in small networks with high accuracies. Finally, guided by matrix conditioning, we provide a method to effectively squeeze models that are already trained. Our techniques reduce the human cost of designing deep learning models and can also reduce training time and the expense of using neural networks for applications.

This paper provides an empirical evaluation of recently developed exploration algorithms within the Arcade Learning Environment (ALE). We study the use of different reward bonuses that incentives exploration in reinforcement learning. We do so by fixing the learning algorithm used and focusing only on the impact of the different exploration bonuses in the agent's performance. We use Rainbow, the state-of-the-art algorithm for value-based agents, and focus on some of the bonuses proposed in the last few years. We consider the impact these algorithms have on performance within the popular game Montezuma's Revenge which has gathered a lot of interest from the exploration community, across the the set of seven games identified by Bellemare et al. (2016) as challenging for exploration, and easier games where exploration is not an issue. We find that, in our setting, recently developed bonuses do not provide significantly improved performance on Montezuma's Revenge or hard exploration games. We also find that existing bonus-based methods may negatively impact performance on games in which exploration is not an issue and may even perform worse than $\epsilon$-greedy exploration.