Filters








167 Hits in 4.2 sec

PALM

Sanjay Krishnan, Eugene Wu
2017 Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics - HILDA'17  
We present Partition Aware Local Model (PALM), which is a tool that learns and summarizes this responsibility structure to aide machine learning debugging.  ...  Queries to PALM are nearly 30x faster than nearest neighbor queries for identifying relevant data, which is a key property for interactive applications.  ...  scalable tools to debug modern machine learning models.  ... 
doi:10.1145/3077257.3077271 dblp:conf/sigmod/Krishnan017 fatcat:aea6e7xw2fbiviupwnxu2kqtty

Estimation and Interpretation of Machine Learning Models with Customized Surrogate Model

Mudabbir Ali, Asad Masood Khattak, Zain Ali, Bashir Hayat, Muhammad Idrees, Zeeshan Pervez, Kashif Rizwan, Tae-Eung Sung, Ki-Il Kim
2021 Electronics  
Machine learning has the potential to predict unseen data and thus improve the productivity and processes of daily life activities.  ...  Notwithstanding its adaptiveness, several sensitive applications based on such technology cannot compromise our trust in them; thus, highly accurate machine learning models require reason.  ...  PALM is a method that can summarize and learn the overall structure of the data provided for machine learning debugging.  ... 
doi:10.3390/electronics10233045 fatcat:vmm2ju7pizf4pcky2kyt3lc7lu

Examining the Multidimensional Learning Affordances of Robotics for Computational Thinking and Science Inquiry [chapter]

2022 Computational Thinking Education in K–12  
This brick, which is in its third iteration, is currently called the EV3. The EV3 is a device that can fit into the palm of an adult's hand (see figure 10 .1).  ...  Importantly, students are learning about the robotic system through these debugging activities.  ... 
doi:10.7551/mitpress/13375.003.0017 fatcat:psxkb3w4q5efpfucff6e7rdoqm

A Survey Of Methods For Explaining Black Box Models [article]

Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Dino Pedreschi, Fosca Giannotti
2018 arXiv   pre-print
Given a problem definition, a black box type, and a desired explanation this survey should help the researcher to find the proposals more useful for his own work.  ...  or implicitly its own definition of interpretability and explanation.  ...  In particular, PALM is a method that is able to learn and summarize the structure of the training dataset to help the machine learning debugging.  ... 
arXiv:1802.01933v3 fatcat:n6ly5sqyjfhwjbcdx3h32cmiqi

Machine Learning Testing: Survey, Landscapes and Horizons [article]

Jie M. Zhang University College London, Nanyang Technological University)
2019 arXiv   pre-print
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research.  ...  ., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and application scenarios (e.g., autonomous driving, machine translation).  ...  This also provided one final stage in the systematic trawling of the literature for relevant work.  ... 
arXiv:1906.10742v2 fatcat:p5c54cy4pjc5flzm7shybk3qxe

User Feedback and Uncertainty in User Guided Binarization

Florian Westphal, Hakan Grahn, Niklas Lavesson
2018 2018 IEEE International Conference on Data Mining Workshops (ICDMW)  
In this paper, we propose guided machine learning as source for suitable guidance strategies, we distinguish between sample selection based and privileged information based strategies and evaluate three  ...  , while the target domain are texts written on palm leaves in Balinese script.  ...  Guided Machine Learning In this paper, guided machine learning (gML) refers to a form of interactive machine learning [22] , [23] , which is concerned only with learning algorithms allowing an external  ... 
doi:10.1109/icdmw.2018.00066 dblp:conf/icdm/WestphalGL18 fatcat:xasvx6kzrbhb5mhkrchwstzk6y

Machine Learning Education for Artists, Musicians, and Other Creative Practitioners

Rebecca Fiebrink
2019 ACM Transactions on Computing Education  
This article aims to lay a foundation for the research and practice of machine learning education for creative practitioners.  ...  technologies, for teaching some of the first courses in the world focused on teaching machine learning to creative practitioners.  ...  ACKNOWLEDGMENTS I would like to thank Kadenze Inc. for the opportunity to teach Machine Learning for Musicians and Artists on their platform, and for the immeasurable support Kadenze personnel have offered  ... 
doi:10.1145/3294008 fatcat:psugtsvr3faxbg4akuhp7hmqiy

Passport: Improving Automated Formal Verification Using Identifiers [article]

Alex Sanchez-Stern and Emily First and Timothy Zhou and Zhanna Kaufman and Yuriy Brun and Talia Ringer
2022 arXiv   pre-print
In the course of building Passport, we encountered and overcame significant challenges unique to building machine-learning-based proof synthesis tools.  ...  Tools that learn from proof corpora to suggest partial or complete proof scripts have just begun to show their promise.  ...  ACKNOWLEDGMENTS We thank Tom Reichel for his help on debugging nondeterminism in model training. This work is supported by DARPA under grant no.  ... 
arXiv:2204.10370v1 fatcat:tia4evlgnra4jj6ayb3jleajxm

Explainable Artificial Intelligence: a Systematic Review [article]

Giulia Vilone, Luca Longo
2020 arXiv   pre-print
This is due to the widespread application of machine learning, particularly deep learning, that has led to the development of highly accurate models but lack explainability and interpretability.  ...  learning', 'interpretable machine learning'.  ...  This has led to the development of a plethora of domain-dependent and context-specific methods for dealing with the interpretation of machine learning (ML) models and the formation of explanations for  ... 
arXiv:2006.00093v4 fatcat:dr26wgxvqrg7diljklhmdjkj7i

DeepBase: Deep Inspection of Neural Networks [article]

Thibault Sellam, Kevin Lin, Ian Yiran Huang, Yiru Chen, Michelle Yang, Carl Vondrick, Eugene Wu
2019 arXiv   pre-print
Recent machine learning research has leveraged statistical methods to identify hidden units that behave (e.g., activate) similarly to human understandable logic, but those analyses require considerable  ...  Although deep learning models perform remarkably well across a range of tasks such as language translation and object recognition, it remains unclear what high-level logic, if any, they follow.  ...  Machine Learning Interpretation: A related field of research seeks to augment machine learning predictions with explanations, to help debugging or augment software produces based on classifier.  ... 
arXiv:1808.04486v4 fatcat:esoixwqd6ndqdkymvoyejwcwr4

in the control room of the banquet

Richard P. Gabriel
2016 Proceedings of the 2016 ACM International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software - Onward! 2016  
As noted learning is generally taken as machine learning these days.  ...  Nevertheless, InkWell has many learned aspects-machine learned at my hands, machine learned by others, and learned through curated and automatically produced dictionaries and databases.  ... 
doi:10.1145/2986012.2986028 dblp:conf/oopsla/Gabriel16 fatcat:xexykohkrrhtddglph5bmbcslu

Reference list of indexed articles

1997 Artificial Intelligence  
Gratch, Book review of Learning Search Control Knowledge: An Explanation-Based Approach (Steve Minton) 50 (1) (1991) 117-127 647. G.  ...  -P Laurent, LAURA, a system to debug student programs 15 (I-2) (1980) 75-122 173.  ... 
doi:10.1016/s0004-3702(97)80123-3 fatcat:k6vuarylb5eprhd53uncv4h4j4

Hitting the distributed computing sweet spot with TSpaces

Tobin J. Lehman, Alex Cozzi, Yuhong Xiong, Jonathan Gottschalk, Venu Vasudevan, Sean Landis, Pace Davis, Bruce Khavar, Paul Bowman
2001 Computer Networks  
For many dierent types of applications, the loose synchronization provided by TSpaces works extremely well.  ...  TSpaces is an excellent tool for building distributed applications, since it provides an asynchronous and anonymous link between multiple clients or services.  ...  We list the eight main uses of TSpaces here, each with an explanation. · Heterogeneous message system.  ... 
doi:10.1016/s1389-1286(00)00178-x fatcat:7ucyyylaxvbglfhalbvapa2sra

Security improvements Zone Routing Protocol in Mobile Ad Hoc Network

Mahsa Seyyedtaj, Mohammad Ali Jabraeil Jamali
2014 International Journal of Computer Applications Technology and Research  
Many secure routing protocols proposed for secure routing either active or reactive, however, both of these protocols have some limitations.  ...  Proactive routing protocols: In it, all the nodes continuously search for routing information with in a network, so that when a route is needed, the route is already known.  ...  Palm OS (Garnet OS) Palm OS was developed by Palm Inc in 1996 especially for PDAs (Personal Digital Assistance). Palm OS was basically designed to work on touch screen GUI.  ... 
doi:10.7753/ijcatr0309.1001 fatcat:n7yb26a6zbgwnpvfmvka3cnpoq

Creating a lightweight user interface description language

Jeffrey Nichols, Brad A. Myers
2009 ACM Transactions on Computer-Human Interaction  
Over six years, we iterated on the design of a language for describing the functionality of appliances, such as televisions, telephones, VCRs, and copiers.  ...  Through this analysis, we hope to provide a useful guide for the designers of future user interface description languages. . 2009.  ...  "play new" function for answering machines.  ... 
doi:10.1145/1614390.1614392 fatcat:t6zt7vfpxnfbjovqfsibl52cha
« Previous Showing results 1 — 15 out of 167 results