Filters








29,688 Hits in 3.9 sec

Human Computation

Edith Law, Luis von Ahn
2011 Synthesis Lectures on Artificial Intelligence and Machine Learning  
With the growth of the Web, human computation systems can now leverage the abilities of an unprecedented number of people via the Web to perform complex computation.  ...  research directions for the future.  ...  debates about the definitions, scope and future directions of human computation.  ... 
doi:10.2200/s00371ed1v01y201107aim013 fatcat:fxuui3q2yrgddf5ewih562zgza

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian (+6 others)
2020 IEEE Transactions on Neural Networks and Learning Systems  
We present JueWu-SL, the first supervised-learning-based artificial intelligence (AI) program that achieves human-level performance in playing multiplayer online battle arena (MOBA) games.  ...  In these matches, we observe that AI learned many high-level human-like game tactics and can execute these tactics well.  ...  We develop local image-like and global image-like features that are extracted from the player hero's local view map and the global minimap, respectively.  ... 
doi:10.1109/tnnls.2020.3029475 pmid:33147150 fatcat:vdpans5ivzgardygdegqjuhwna

StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation [article]

Xiang Li, Lili Mou, Rui Yan, Ming Zhang
2016 arXiv   pre-print
Existing open-domain human-computer conversation systems are typically passive: they either synthesize or retrieve a reply provided a human-issued utterance.  ...  We design a pipeline to determine when, what, and how to introduce new content during human-computer conversation.  ...  We define the weight matrix by a relevance scoring function φ(q, r) between queries and replies. φ(·, ·) was learned via a learning-to-rank model similar to Burges et al. [2005] with rich features including  ... 
arXiv:1604.04358v1 fatcat:gdmb7eh55nbsdcc5inlregfp2i

Human-in-the-Loop Interpretability Prior [article]

Isaac Lage, Andrew Slavin Ross, Been Kim, Samuel J. Gershman, Finale Doshi-Velez
2018 arXiv   pre-print
In this work, we optimize for interpretability by directly including humans in the optimization loop.  ...  Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required.  ...  All authors thank Emily Chen and Jeffrey He for their support with the experimental interface, and Weiwei Pan and the Harvard DTaK group for many helpful discussions and insights.  ... 
arXiv:1805.11571v2 fatcat:q46wa3yrfve6pacuwqqs4bjreq

Contextual influence on confidence judgments in human reinforcement learning [article]

Mael Lebreton, Karin Bacily, Stefano Palminteri, Jan B Engelmann
2018 bioRxiv   pre-print
In two experiments, we demonstrate that participants are more confident in their choices when learning to seek gains compared to avoiding losses.  ...  The biasing effect of context-value on confidence, also recently observed in the context of incentivized perceptual decision-making, is therefore domain-general, with likely important functional consequences  ...  Computational modelling Reinforcement-learning model The approach for the reinforcement-learning modelling is identical to the one followed in Palminteri and colleagues (2015) .  ... 
doi:10.1101/339382 fatcat:yngzqphgffc2dmgk5i6f4rs6dm

Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences [article]

Erdem Bıyık, Dylan P. Losey, Malayandi Palan, Nicholas C. Landolfi, Gleb Shevchuk, Dorsa Sadigh
2021 arXiv   pre-print
As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers.  ...  (e.g., comparative rankings) are actively elicited.  ...  We draw from work on active learning and inverse reinforcement learning to synthesize human data sources while maximizing information gain.  ... 
arXiv:2006.14091v2 fatcat:5bvuyqpte5hifaluozij2jnmla

Human Stigmergic Problem Solving [chapter]

2021 Cultural-Historical Perspectives on Collective Intelligence  
For example, there are dedicated Community Question Answering (CQA) sites, markets for answering questions that involve people with particular expertise.  ...  By using a dynamic ranking system, participants can vote at different points of time. It is also possible to view how previous users have ranked the ideas.  ... 
doi:10.1017/9781108981361.006 fatcat:lgkgbw3cffeglhkkw7cpml6c6i

Visual Geometric Skill Inference by Watching Human Demonstration [article]

Jun Jin, Laura Petrich, Zichen Zhang, Masood Dehghan, Martin Jagersand
2020 arXiv   pre-print
We propose a graph based kernel regression method to directly infer the underlying association constraints from human demonstration video using Incremental Maximum Entropy Inverse Reinforcement Learning  ...  Our method removes the need for tedious feature selection and robust feature trackers required in traditional approaches (e.g. feature-based visual servoing).  ...  It computes object spatial motion changes via feature matching and then forms a new task goal configuration used to generate motion primitives by a trajectory-based learning from demonstration (LfD) method  ... 
arXiv:1911.04418v2 fatcat:peogyv27pfd7viorwjq4wkrtqm

Contextual influence on confidence judgments in human reinforcement learning

Maël Lebreton, Karin Bacily, Stefano Palminteri, Jan B. Engelmann, Peter E. Latham
2019 PLoS Computational Biology  
To simultaneously account for this pattern of choices and confidence judgments, we propose that individuals learn context-values, which approximate the average expected-value of choice options.  ...  After a fixation cross, participants viewed a couple of abstract symbols displayed on both sides of a computer screen and had to choose between them.  ...  Acknowledgments We thank Caspar Lusink for his help with data collection in experiment 3. Author Contributions  ... 
doi:10.1371/journal.pcbi.1006973 fatcat:jjsbdd42ejcrtjmefecaohyymq

Human Language Technology

Mark Liberman, Charles Wayne
2020 The AI Magazine  
Human language technology encompasses a wide array of speech and text processing capabilities.  ...  working in parallel took advantage of increasingly large and diverse sets of linguistic data and rapidly increasing computational power to develop and use increasingly sophisticated forms of machine learning  ...  Like many other AI problems, automatic transcription requires global optimization.  ... 
doi:10.1609/aimag.v41i2.5297 fatcat:fa3aaxaeb5dplapdkatosb7waa

Object Referring in Videos with Language and Human Gaze [article]

Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
2018 arXiv   pre-print
Humans also gaze at the object when they issue a referring expression. Existing works for OR mostly focus on static images only, which fall short in providing many such cues.  ...  This paper addresses OR in videos with language and human gaze.  ...  Acknowledgement: The work is supported by Toyota via project TRACE-Zurich. We also thank Vaishakh Patil and Prashanth Chandran for helpful comments.  ... 
arXiv:1801.01582v2 fatcat:ujfw5df5w5dhjjxtnf2zvbgbx4

Course redesign to promote local and global experiential learning about human occupation: Description and evaluation of a pilot effort

Rebecca M. Aldrich
2015 South African Journal of Occupational Therapy  
Globalisation heightens the need for diverse learning experiences regarding human occupation.  ...  It is important to consider how experiential learning fits within course objectives, as well as how technology enables or inhibits experiential learning across local and global contexts.  ...  I am also grateful to Debie Lohe and the rest of the Reinert Centre for Transformative Teaching and Learning for the opportunity to hold the Innovative Teaching Fellowship and teach in the Learning Studio  ... 
doi:10.17159/2310-3833/2015/v45no1a10 fatcat:ynxi4squenawldwbkfgyaqbno4

Partial success in closing the gap between human and machine vision [article]

Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A. Wichmann, Wieland Brendel
2021 arXiv   pre-print
Our results give reason for cautious optimism: While there is still much room for improvement, the behavioural difference between human and machine vision is narrowing.  ...  To answer this question, we tested human observers on a broad range of out-of-distribution (OOD) datasets, recording 85,120 psychophysical trials across 90 participants.  ...  Mutschler, David-Elias Künstle for feedback on the manuscript; Santiago Cadena for sharing a PyTorch implementation of SimCLR; Katherine Hermann and her collaborators for providing supervised SimCLR baselines  ... 
arXiv:2106.07411v2 fatcat:kd4es6yzirggnht65mvpqwz4yu

Object Referring in Videos with Language and Human Gaze

Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Humans also gaze at the object when they issue a referring expression. Existing works for OR mostly focus on static images only, which fall short in providing many such cues.  ...  This paper addresses OR in videos with language and human gaze.  ...  Acknowledgement: The work is supported by Toyota via project TRACE-Zurich. We also thank Vaishakh Patil and Prashanth Chandran for helpful comments.  ... 
doi:10.1109/cvpr.2018.00434 dblp:conf/cvpr/VasudevanDG18 fatcat:ybr34relevhgvoby2pdquu6szm

Microinnovations in Human-Technology Interaction

Pertti Saariluoma
2011 Human Technology: An Interdisciplinary Journal on Humans in ICT Environments  
Although this approach of one leader directing a group was representative of the 20 th century, the new, globally interconnected context sets the stage for the expectation that leadership is to be less  ...  Human thinking opens the potential for people to reach their goals in life when such solutions are not currently available (Newell & Simon, 1972) .  ...  of programmers (volunteering) for the tasks that best match their abilities.  ... 
doi:10.17011/ht/urn.201152310895 fatcat:n77f6bft25hwdoexyhbhosizae
« Previous Showing results 1 — 15 out of 29,688 results