The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users Deep Learning for Predicting Human Strategic Behavior Deep Convolutional Neural Networks On Multichannel Time Series For Human Activity Recognition

In this paper, we proposed a new method to automate feature extraction for the human activity recognition task. The proposed method builds a new deep architecture for the CNN to investigate the multichannel time series data. This deep architecture mainly employs the convolution and pooling operations to capture the salient patterns of the sensor signals at different time scales. All identified salient patterns are systematically unified among multiple channels and finally mapped into the different classes of human activities. The key advantages of the proposed method are: i) feature extraction is performed in task dependent and non hand-crafted manners; ii) extracted features have more discriminative power w.r.t. the classes of human activities; iii) feature extraction and classification are unified in one model so their performances are mutually enhanced. In the experiments, we demonstrate that the proposed CNN method outperforms other state-of-the-art methods, and we therefore believe that the proposed method can serve as a competitive tool of feature learning and classi- fication for the HAR problems. Social Fingerprinting: detection of spambot groups through DNA-inspired behavioral modeling

Spambot detection in online social networks is a long-lasting challenge involving the study and design of detection techniques capable of efficiently identifying ever-evolving spammers. Recently, a new wave of social spambots has emerged, with advanced human-like characteristics that allow them to go undetected even by current state-of-the-art algorithms. In this paper, we show that efficient spambots detection can be achieved via an in-depth analysis of their collective behaviors exploiting the digital DNA technique for modeling the behaviors of social network users. Inspired by its biological counterpart, in the digital DNA representation the behavioral lifetime of a digital account is encoded in a sequence of characters. Then, we define a similarity measure for such digital DNA sequences. We build upon digital DNA and the similarity between groups of users to characterize both genuine accounts and spambots. Leveraging such characterization, we design the Social Fingerprinting technique, which is able to discriminate among spambots and genuine accounts in both a supervised and an unsupervised fashion. We finally evaluate the effectiveness of Social Fingerprinting and we compare it with three state-of-the-art detection algorithms. Among the peculiarities of our approach is the possibility to apply off-the-shelf DNA analysis techniques to study online users behaviors and to efficiently rely on a limited number of lightweight account characteristics. Maintaining cooperation in complex social dilemmas using deep reinforcement learning

Much is known about how cooperation can be stabilized in the simplest of such settings: repeated Prisoner's Dilemma games. However, there is relatively little work on generalizing these insights to more complex situations. We start to fill this gap by showing how to use modern reinforcement learning methods to generalize a highly successful Prisoner's Dilemma strategy: tit-for-tat.