522,952 Hits in 6.7 sec

The Zen of Graduate-level Programming [article]

Zubair Nabi
2014 arXiv   pre-print
In the second half, all of these concepts are employed as building blocks to solve real-world problems from data mining, natural language processing, computer vision, and other fields.  ...  To remedy this, we present the blueprint and execution of a graduate level course in programming, designed specifically to cater to the needs of graduate students with a diverse background both in CS and  ...  In the second half of the course, these building blocks are used to solve real-world problems from machine learning, NLP, graph theory, and computer vision, to name a few.  ... 
arXiv:1405.2489v1 fatcat:42kzlc64cjfijeitarstao5k7m

Programming by Examples: PL Meets ML [chapter]

Sumit Gulwani, Prateek Jain
2017 Lecture Notes in Computer Science  
Programming by Examples (PBE) involves synthesizing intended programs in an underlying domain-specific language from examplebased specifications.  ...  There are three key components in a PBE system. (i) A search algorithm that can efficiently search for programs that are consistent with the examples provided by the user.  ...  in this article related to using ML techniques for search and ranking.  ... 
doi:10.1007/978-3-319-71237-6_1 fatcat:nou2fnkpt5elfj3ohaunnfmy7y

A reply to Pazzani's book review of "Inductive Logic Programming: Techniques and Applications"

Nada Lavrač, Sašo Džeroski
1996 Machine Learning  
For example, while learning recursive rules (inverted implication) and predicate invention have received a lot of attention within the ILP community, few practical results exist so far.  ...  Inductive Logic Programming (ILP) is concerned with learning first-order rules formulated in the language of logic programs.  ...  For example, while learning recursive rules (inverted implication) and predicate invention have received a lot of attention within the ILP community, few practical results exist so far.  ... 
doi:10.1007/bf00116902 fatcat:qzow2vrflfhujajeffo3gmbfdu


1996 Machine Learning  
example, using only a few examples of the proper sequence of motions.  ...  This paper has a tutorial nature in that concepts from engineering robotics, such as closed-loop stability and PID control are clearly described.  ... 
doi:10.1007/bf00117441 fatcat:ai7xtfzizbajlddbz3s3uigkem

TF-Coder: Program Synthesis for Tensor Manipulations [article]

Kensen Shi, David Bieber, Rishabh Singh
2020 arXiv   pre-print
In this work, we present a tool called TF-Coder for programming by example in TensorFlow.  ...  However, these libraries also come with steep learning curves, since programming in these frameworks is quite different from traditional imperative programming with explicit loops and conditionals.  ...  ACKNOWLEDGMENTS The authors thank Charles Sutton and the other members of the program synthesis team at Google Brain for helpful discussions.  ... 
arXiv:2003.09040v3 fatcat:cvgj7xrshfhxhhqjpsyv7nyjf4

ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback [article]

Mike Wu, Noah Goodman, Chris Piech, Chelsea Finn
2021 arXiv   pre-print
In this paper, we instead frame the problem of providing feedback as few-shot classification, where a meta-learner adapts to give feedback to student code on a new programming question from just a few  ...  On a suite of few-shot natural language processing tasks, we match or outperform state-of-the-art performance.  ...  Meta-learning approaches have demonstrated promising results on such problems by learning how to quickly learn a classifier from a few examples.  ... 
arXiv:2107.14035v2 fatcat:4x2ojsdqija4zn4n4yvqlajlby

Behavior construction and refinement from high-level specifications

Andrew J. Martignoni III, William D. Smart, Douglas W. Gage
2004 Mobile Robots XVII  
Mobile robots are excellent examples of systems that need to show a high level of autonomy.  ...  We need a system that will (a) allow re-tasking, and (b) allow adaptation of the behavior to the specific conditions in the field. In this paper we concentrate on (b).  ...  In particular, we show high-level feedback from a human observer can be combined with machine learning techniques to improve the behavior over time.  ... 
doi:10.1117/12.568865 dblp:conf/mr/MartignoniS02 fatcat:ldtmee2i65agfpisrsq2mkrjzi

Teaching Introductory Quantitative Research Methods to Doctoral Students in Educational Leadership: Using Real Data to Improve Statistical Literacy

Serena J. Salloum, Tamara V. Young, Rebecca D. Brown
2016 International Research in Higher Education  
Survey data confirms students favorably support the use of real data in statistics courses, despite challenges to learning statistical software and time constraints that inhibit full engagement in the  ...  the course through the specific pedagogical approach of using real secondary data.  ...  For example, we run descriptive statistics of population across a few variables to show the "true" values.  ... 
doi:10.5430/irhe.v1n2p203 fatcat:7h43jjrb6bbj3bxzfvcmbtsi4i

Neurosymbolic Programming

Swarat Chaudhuri, Kevin Ellis, Oleksandr Polozov, Rishabh Singh, Armando Solar-Lezama, Yisong Yue
2021 Foundations and Trends® in Programming Languages  
Like in classic machine learning, the goal here is to learn functions from data.  ...  However, these functions are represented as programs that can use neural modules in addition to symbolic primitives and are induced using a combination of symbolic search and gradient-based optimization  ...  At the same time, concerns remain about the use of deep neural networks in real-world problem domains (Marcus and Davis, 2019) .  ... 
doi:10.1561/2500000049 fatcat:yf7hfvpborh73ht3ukw7ok7axm

Inductive programming meets the real world

Sumit Gulwani, José Hernández-Orallo, Emanuel Kitzelmann, Stephen H. Muggleton, Ute Schmid, Benjamin Zorn
2015 Communications of the ACM  
Key insights • Real-world applications emerge with spreadsheet tools, intelligent program tutors, and robotics. • Learning from few examples is possible because users and systems share the same background  ...  Inductive Programming has a long research tradition and recent developments demonstrate it can liberate users from many tasks of this kind.  ...  Flash Fill is able to learn a large variety of quite complex programs from only a few examples because of incorporation of inductive programming methods.  ... 
doi:10.1145/2736282 fatcat:oods62zxrnfejeql6d3efmx52a

Gestures that people can understand and use

Carmelo Ardito, Maria Francesca Costabile, Hans-Christian Jetter
2014 Journal of Visual Languages and Computing  
Today, thanks to advances in computer vision that permit real-time body, hand, and finger tracking, it is also possible to recognize human motion from a distance.  ...  few seconds.  ...  Today, thanks to advances in computer vision that permit real-time body, hand, and finger tracking, it is also possible to recognize human motion from a distance.  ... 
doi:10.1016/j.jvlc.2014.07.002 fatcat:or5pjwcimjfsvoas5ygr7mbxu4

Learning a Natural Language Interface with Neural Programmer [article]

Arvind Neelakantan, Quoc V. Le, Martin Abadi, Andrew McCallum, Dario Amodei
2017 arXiv   pre-print
Learning a natural language interface for database tables is a challenging task that involves deep language understanding and multi-step reasoning.  ...  To our knowledge, this paper presents the first weakly supervised, end-to-end neural network model to induce such programs on a real-world dataset.  ...  Arvind Neelakantan is supported by a Google PhD fellowship in machine learning.  ... 
arXiv:1611.08945v4 fatcat:th73j7sqtzgfrl6ogf72dj2lc4

Preface to special issue on Inductive Logic Programming, ILP 2017 and 2018

Nicolas Lachiche, Christel Vrain, Fabrizio Riguzzi, Elena Bellodi, Riccardo Zese
2019 Machine Learning  
The system iteratively learns low cost logic programs, from a relatively small numbers of examples, using iterative descent, each time further restricting the hypothesis space.  ...  A few trends in ILP 2017-2018 can be identified.  ... 
doi:10.1007/s10994-019-05790-6 fatcat:mbvnu2znvfezldw3owtu67rasy

Collaborative and Constructive Learning of Elementary School Children in Experiental Learning Spaces along the Virtuality Continuum [chapter]

Huberta Kritzenberger, Thomas Winkler, Michael Herczeg
2002 Berichte des German Chapter of the ACM  
Learning is an active, constructive and collaborative process, where people construct knowledge from their experiences in the world.  ...  During the process of constructing and interacting with the learning space along a virtuality continuum the children make learning experiences, which can be interpreted in a semiotic way and which allows  ...  Acknowledgements The project is funded by the German "Bund-Länder Commission for Educational Planning and Research Promotion" (BLK) within the general funding program "Culture in the Media Age".  ... 
doi:10.1007/978-3-322-89884-5_12 fatcat:5m7qg274sjab5psmon62qpms3e

Performance Assessment Design Principles Gleaned from Constructivist Learning Theory (Part 1)

2009 TechTrends  
Design a testing program that collects multiple data points (scores) from as many contexts as is feasible. 4. When possible, offer different modes of assessment over time. 5.  ...  Learning and assessment should be based upon the complex and integrated nature of the real world.  ... 
doi:10.1007/s11528-009-0242-5 fatcat:poxp3ym3pjb27inirvezethkha
« Previous Showing results 1 — 15 out of 522,952 results