Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

The measurement of meaning

/pdf/neural-networks-and-deep-learning-3ccs3ain8p.pdf

Neural Networks and Deep Learning

人教版高中英语新课程教材中,语言运用（Using Language）是每个单元必不可少的部分,提供了围绕单元中心话题的听、说、读、写的综合性练习,是单元中心话题的延续和升华.如何设计Using Language部分的教学,使自己的教学模式既不落俗套,又能真正体现新课程标准所倡导的教学理念,正是广大一线英语教师一直努力探索的问题.

打磨Using Language,倡导新理念

Objective: We evaluate and quantify the effects of human, robot, and environmental factors on perceived trust in human-robot interaction (HRI)Background: To date, reviews of trust in HRI have been

/pdf/a-meta-analysis-of-factors-affecting-trust-in-human-robot-1305er4ix4.pdf

A meta-analysis of factors affecting trust in human-robot interaction.

To seamlessly integrate into the human physical and social environment, robots must display appropriate proxemic behavior - that is, follow societal norms in establishing their physical and psychological distancing with people. Social-scientific theories suggest competing models of human proxemic behavior, but all conclude that individuals' proxemic behavior is shaped by the proxemic behavior of others and the individual's psychological closeness to them. The present study explores whether these models can also explain how people physically and psychologically distance themselves from robots and suggest guidelines for future design of proxemic behaviors for robots. In a controlled laboratory experiment, participants interacted with Wakamaru to perform two tasks that examined physical and psychological distancing of the participants. We manipulated the likeability (likeable/dislikeable) and gaze behavior (mutual gaze/averted gaze) of the robot. Our results on physical distancing showed that participants who disliked the robot compensated for the increase in the robot's gaze by maintaining a greater physical distance from the robot, while participants who liked the robot did not differ in their distancing from the robot across gaze conditions. The results on psychological distancing suggest that those who disliked the robot also disclosed less to the robot. Our results offer guidelines for the design of appropriate proxemic behaviors for robots so as to facilitate effective human-robot interaction.

Human-robot proxemics: physical and psychological distancing in human-robot interaction

During conversations, speakers establish their and others' participant roles (who participates in the conversation and in what capacity)--or "footing" as termed by Goffman-using gaze cues. In this paper, we study how a robot can establish the participant roles of its conversational partners using these cues. We designed a set of gaze behaviors for Robovie to signal three kinds of participant roles: addressee, bystander, and overhearer. We evaluated our design in a controlled laboratory experiment with 72 subjects in 36 trials. In three conditions, the robot signaled to two subjects, only by means of gaze, the roles of (1) two addressees, (2) an addressee and a bystander, or (3) an addressee and an overhearer. Behavioral measures showed that subjects' participation behavior conformed to the roles that the robot communicated to them. In subjective evaluations, significant differences were observed in feelings of groupness between addressees and others and liking between overhearers and others. Participation in the conversation did not affect task performance-measured by recall of information presented by the robot-but affected subjects' ratings of how much they attended to the task.

Footing in human-robot conversations: how robots might shape participant roles using gaze cues

Engaging storytelling is a necessary skill for humanoid robots if they are to be used in education and entertainment applications Storytelling requires that the humanoid robot be aware of its audience and able to direct its gaze in a natural way In this paper, we explore how human gaze can be modeled and implemented on a humanoid robot to create a natural, human-like behavior for storytelling Our gaze model integrates data collected from a human storyteller and a discourse structure model developed by Cassell and her colleagues for human-like conversational agents (1994) We used this model to direct the gaze of a humanoid robot, Honda's ASIMO, as he recited a Japanese fairy tale using a pre-recorded human voice We assessed the efficacy of this gaze algorithm by manipulating the frequency of ASIMO's gaze between two participants and used pre and post questionnaires to assess whether participants evaluated the robot more positively and did better on a recall task when ASIMO looked at them more We found that participants performed significantly better in recalling ASIMO's story when the robot looked at them more Our results also showed significant differences in how men and women evaluated ASIMO based on the frequency of gaze they received from the robot Our study adds to the growing evidence that there are many commonalities between human-human communication and human-robot communication

/pdf/a-storytelling-robot-modeling-and-evaluation-of-human-like-2t3euxpoaz.pdf

A Storytelling Robot: Modeling and Evaluation of Human-like Gaze Behavior

Robots are becoming increasingly integrated into the workplace, impacting organizational structures and processes, and affecting products and services created by these organizations. While robots promise significant benefits to organizations, their introduction poses a variety of design challenges. In this paper, we use ethnographic data collected at a hospital using an autonomous delivery robot to examine how organizational factors affect the way its members respond to robots and the changes engendered by their use. Our analysis uncovered dramatic differences between the medical and post-partum units in how people integrated the robot into their workflow and their perceptions of and interactions with it. Different patient profiles in these units led to differences in workflow, goals, social dynamics, and the use of the physical environment. In medical units, low tolerance for interruptions, a discrepancy between the perceived cost and benefits of using the robot, and breakdowns due to high traffic and clutter in the robot's path caused the robot to have a negative impact on the workflow and staff resistance. On the contrary, post-partum units integrated the robot into their workflow and social context. Based on our findings, we provide design guidelines for the development of robots for organizations.

/pdf/robots-in-organizations-the-role-of-workflow-social-and-2ra3zik5tk.pdf

Robots in organizations: the role of workflow, social, and environmental factors in human-robot interaction

Embodied agents hold great promise as educational assistants, exercise coaches, and team members in collaborative work. These roles require agents to closely monitor the behavioral, emotional, and mental states of their users and provide appropriate, effective responses. Educational agents, for example, will have to monitor student attention and seek to improve it when student engagement decreases. In this paper, we draw on techniques from brain-computer interfaces (BCI) and knowledge from educational psychology to design adaptive agents that monitor student attention in real time using measurements from electroencephalography (EEG) and recapture diminishing attention levels using verbal and nonverbal cues. An experimental evaluation of our approach showed that an adaptive robotic agent employing behavioral techniques to regain attention during drops in engagement improved student recall abilities 43% over the baseline regardless of student gender and significantly improved female motivation and rapport. Our findings offer guidelines for developing effective adaptive agents, particularly for educational settings.

http://pages.cs.wisc.edu/~bilge/pubs/2012/CHI12-Szafir.pdf

Bilge Mutlu

Papers

Human-robot proxemics: physical and psychological distancing in human-robot interaction

Footing in human-robot conversations: how robots might shape participant roles using gaze cues

A Storytelling Robot: Modeling and Evaluation of Human-like Gaze Behavior

Robots in organizations: the role of workflow, social, and environmental factors in human-robot interaction

Pay attention!: designing adaptive agents that monitor and improve user engagement