A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Show Your Work: Scratchpads for Intermediate Computation with Language Models
[article]
2021
arXiv
pre-print
Preserved Fulltext
On a series of increasingly complex tasks ranging from long addition to the execution of arbitrary programs, we show that scratchpads dramatically improve the ability of language models to perform multi-step ...
In particular, we train transformers to perform multi-step computations by asking them to emit intermediate computation steps into a "scratchpad". ...
ACKNOWLEDGMENTS We thank Fraser Greenlee for constructing the single-line programs dataset, and Kevin Murphy for bringing this dataset to our attention. ...
arXiv:2112.00114v1
fatcat:qk5u752x5bdvneqemsuoy7eqke
:{unav)
2012
Data mining and knowledge discovery
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper (1) explains the cube and roll-up operators, (2) shows how they fit in SQL, (3) explains how users can define new aggregate functions for cubes, and (4) discusses efficient techniques to compute ...
Super-aggregates are computed by aggregating the N -cube to lower dimensional spaces. ...
Finally, the end() call computes the aggregate from the scratchpad values, deallocates the scratchpad and returns the result. ...
doi:10.1023/a:1009726021843
fatcat:ylzvngqvfrglrkmg3e7me6ateq
A domain-specific supercomputer for training deep neural networks
2020
Communications of the ACM
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Google's TPU supercomputers train deep neural networks 50x faster than general-purpose supercomputers running a high-performance computing benchmark. ...
Table 4 shows the speedup from the fusion optimization on 2D data is from 1.8 to 6.3. The TF intermediate form for XLA has thousands of ops. ...
Like many systems that map from domain-specific languages to code, XLA integrates a high-level library and a compiler. A TF front end generates code in an intermediate representation for XLA. ...
doi:10.1145/3360307
fatcat:xomnv3wdebdxphccmfhccapcwa
A review of mathematica
1992
Journal of symbolic computation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The Mathematica computer system is reviewed from the perspective of its contributions to symbolic and algebraic computation, as well as its stated goals. ...
Using PostScript as a device-independent intermediate form for plots is somewhat novel; other programs (including Maple and Macsyma) tend to use PostScript only for communicating with hard-copy devices ...
Group 1990 , and AXIOM , (previously referred to as Scratchpad II (Computer Algebra Group (1988) )). ...
doi:10.1016/s0747-7171(10)80011-2
fatcat:m54bnhziabga7bog4uwaykzzbe
Amanuensis: The Programmer's Apprentice
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
As a concrete example we focus on digital assistants that learn from continuous dialog with an expert software engineer while providing initial value as powerful analytical, computational and mathematical ...
Over time these savants learn cognitive strategies (domain-relevant problem solving skills) and develop intuitions (heuristics and the experience necessary for applying them) by learning from their expert ...
works of its own invention, novel but consistent with your taste and sensibilities. ...
arXiv:1807.00082v2
fatcat:piwexqa2xvgg5ec5xwkswstswy
Prutor: A System for Tutoring CS1 and Collecting Student Programs for Analysis
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This system thus serves as a platform for tutoring as well as data collection for researchers. ...
These intermediate versions of the student programs provide the instructors (and data analysts) a view of the students' approach to solving programming problems. ...
In general, in order to allow the system to work for a new imperative programming language, the only modification required is to change the configuration files. ...
arXiv:1608.03828v1
fatcat:r3wstog2d5ehba6jscmlqi5pqq
PIMP My Many-Core: Pipeline-Integrated Message Passing
2020
International journal of parallel programming
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To improve the scalability, several many-core architectures use message passing instead of shared memory accesses for communication. ...
PIMP was integrated into the FPGA model of a classical single issue RISC pipeline to show the small hardware costs compared with other register-level message passing architectures. ...
For example, one of the first message passing many-cores, the Intel Single-chip Cloud Computer (SCC) [13] , provides so-called Message Passing Buffers (MPBs), small scratchpad memories tightly coupled ...
doi:10.1007/s10766-020-00685-9
fatcat:hyabinpgkjdmjdyu2347oh5ukm
NVMExplorer: A Framework for Cross-Stack Comparisons of Embedded Non-Volatile Memories
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This work evaluates eNVM-based storage for a range of application and system contexts including machine learning on the edge, graph analytics, and general purpose cache hierarchy, in addition to describing ...
Repeated off-chip memory accesses to DRAM drive up operating power for data-intensive applications, and SRAM technology scaling and leakage power limits the efficiency of embedded memories. ...
Traffic patterns are extracted from throughput and accesses reported for the compute stream of a domain-specific graph processing accelerator utilizing an 8MB eDRAM scratchpad [52] . ...
arXiv:2109.01188v2
fatcat:h7jx7rulzbgtjgb55zzp3cdi2a
Concurrent Computing in the Many-core Era (Dagstuhl Seminar 15021)
2015
Dagstuhl Reports
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This seminar is a successor to Dagstuhl Seminars 08241 "Transactional memory: From implementation to application" and 12161 "Abstractions for scalable multicore computing", respectively held in June 2008 ...
This report documents the program and the outcomes of Dagstuhl Seminar 15021 "Concurrent computing in the many-core era". ...
The work leads to several research questions about parallel programming models and runtimes for popular dynamic languages with none or very limited support for parallel execution such as JavaScript, Ruby ...
doi:10.4230/dagrep.5.1.1
dblp:journals/dagstuhl-reports/PhilippsenFSM15
fatcat:owcmta65hzb5vmglwq3dwzbehy
BioVeL: a virtual laboratory for data analysis and modelling in biodiversity science and ecology
2016
BMC Ecology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We developed and improved more than 60 Web services with significant potential in many different kinds of data analysis and modelling tasks. ...
; for on-line collaboration through sharing of workflows and workflow runs; for experiment documentation through reproducibility and repeatability; and for computational support via seamless connections ...
We thank you for your contribution. We acknowledge the contribution of Yannick Legré, who contributed to the conception and design of the work but ultimately was unable to participate in the project. ...
doi:10.1186/s12898-016-0103-y
pmid:27765035
pmcid:PMC5073428
fatcat:kphzgb67bzh4tdnwchbkvf2nvq
Can language models learn from explanations in context?
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Large language models can perform new tasks by adapting to a few in-context examples. For humans, rapid learning from examples can benefit from explanations that connect examples to task principles. ...
We then show that explanations tuned for performance on a small validation set offer substantially larger benefits; building a prompt by selecting examples and explanations together substantially improves ...
Acknowledgements We thank Dani Yogatama and Neil Rabinowitz for helpful comments and suggestions, as well as the team that trained the language models. ...
arXiv:2204.02329v1
fatcat:iwqbt3lpmnahtcspl2vmig5zom
A framework for constructing cognition ontologies using WordNet, FrameNet, and SUMO
2015
Cognitive Systems Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The next section discusses the objectives of science ontologies and includes examples for psychoses and for 17 emotion. ...
This article 12 supports that objective by proposing a framework for constructing cognition ontologies by using WordNet, FrameNet, and the Sug-13 gested Upper Merged Ontology (SUMO). ...
From Barrouillet et al. (2011).The rationale for this claim is that interference in Kahn-1095 eman's capacity model occurs when the demand for capac-1096 ity exceeds the supply. ...
doi:10.1016/j.cogsys.2014.06.001
fatcat:dpiwlklhgfcxnjn3ru32b646tm
Identifying middle school students' challenges in computational thinking-based science learning
2016
Research and Practice in Technology Enhanced Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present a research study with CTSiM (Computational Thinking in Simulation and Modeling)-computational thinking-based learning environment for K-12 science, where students build and simulate ...
We investigate a set of core challenges (both computational and science domain related) that middle school students face when working with CTSiM, how these challenges evolve across different modeling activities ...
This work was supported by the NSF (NSF Cyber-learning grant #1124175 and #1441542). ...
doi:10.1186/s41039-016-0036-2
pmid:30613246
pmcid:PMC6302855
fatcat:7eksr6d635h63nzmoxfhqbsxo4
A memory theoretic approach for investigating the roles of language and intuition in mathematical thinking activities
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Ongoing mathematical activities both elementary and advanced, demand working memory resources. ...
But these beliefs are usually in a big contrast with the recent cognitive theoretic findings concerning mathematics. ...
Hence, lengthy and complicated computations with infinite sums and series are replaced by formal computations with integrals. ...
arXiv:1910.00003v1
fatcat:m3nfald5yvd25ioexblh3vswjq
Expressing Parallelism
[chapter]
2020
Data Parallel C++
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We already know how to place code (Chapter 10.1007/978-1-4842-5574-2_2) and data (Chapter 10.1007/978-1-4842-5574-2_3) on a device—all we must do now is engage in the art of deciding what to do with it ...
explicitly managed "scratchpad" memories. ...
Choosing a Kernel Form Choosing between the different kernel forms is largely a matter of personal preference and heavily influenced by prior experience with other parallel programming models and languages ...
doi:10.1007/978-1-4842-5574-2_4
fatcat:ppar5yv5nfgbjiclwwmw74eeua
« Previous
Showing results 1 — 15 out of 94 results