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.
Filters
LoopInvGen: A Loop Invariant Generator based on Precondition Inference
[article]
2019
arXiv
pre-print
Preserved Fulltext
Other Versions
Instead, we start with no initial features, and use program synthesis techniques to grow the set on demand. ...
LoopInvGen is an efficient implementation of the inference technique originally proposed in our earlier work on PIE (https://doi.org/10.1145/2908080.2908099). ...
We extend the data-driven paradigm for inferring sufficient loop invariants. ...
arXiv:1707.02029v4
fatcat:mywfv2j3x5c7vdkxpvq67cjx5e
Precondition Inference for Peephole Optimizations in LLVM
[article]
2017
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 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper proposes ALIVE-INFER, a data-driven approach that infers preconditions for peephole optimizations expressed in Alive. ...
ALIVE-INFER reports both a weakest precondition and a set of succinct partial preconditions to the developer. ...
Data-driven Precondition Inference with Learned Features. ...
arXiv:1611.05980v3
fatcat:3x74opq4ffeatovilhfmqbslze
Interactions between human orbitofrontal cortex and hippocampus support model-based inference
2020
PLoS Biology
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.
Here, we used a sensory preconditioning task and pattern-based neuroimaging to study this question. ...
Importantly, inference was accompanied by representations of associated cues and inferred outcomes in the OFC, as well as by increased HPC-OFC connectivity. ...
Acknowledgments The authors thank Rachel Reynolds and Devyn Smith for assistance in fMRI data acquisition.
Author Contributions Conceptualization: Fang Wang, Geoffrey Schoenbaum, Thorsten Kahnt. ...
doi:10.1371/journal.pbio.3000578
pmid:31961854
fatcat:r2zvxqrd7vgg5eyrrure7ikwm4
Orbitofrontal Cortex Supports Behavior and Learning Using Inferred But Not Cached Values
2012
Science
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.
We found that the orbitofrontal cortex is critical for both value-based behavior and learning when value must be inferred but not when a cached value is sufficient. ...
including how to obtain the expected reward, its unique form and features, and current value. ...
If the OFC is involved in behavior that requires inferred value, then inactivating it at the time of this test should prevent behavior driven by this preconditioned cue, while leaving unimpaired behavior ...
doi:10.1126/science.1227489
pmid:23162000
pmcid:PMC3592380
fatcat:gvlb2uhl2vcchcw3l55fzijl3u
On Scaling Data-Driven Loop Invariant Inference
[article]
2020
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
Although static analyses to infer invariants have been studied for over forty years, recent years have seen a flurry of data-driven invariant inference techniques which guess invariants from examples instead ...
In this paper, we study these scalability issues and address them in our tool oasis that improves the scale of data-driven invariant inference and outperforms state-of-the-art systems on benchmarks from ...
Data-driven invariant inference techniques can handle challenging loops with confusing program text by applying ML techniques to mine patterns directly from data. ...
arXiv:1911.11728v2
fatcat:qtqbwjoln5f6fnetgf7u5gp24i
Learning theory: A driving force in understanding orbitofrontal function
2014
Neurobiology of Learning and Memory
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.
The use of these procedures has revealed OFC's unique role in forming and integrating information about specific features of events and outcomes to drive behavior and learning. ...
These studies highlight the power and importance of learning theory principles in guiding neuroscience research. ...
Rather, this deficit was specific to new learning driven by changes in specific reward features. ...
doi:10.1016/j.nlm.2013.06.003
pmid:23770491
pmcid:PMC3800485
fatcat:ojzrvupep5dgnk5bm4zdqpy7oy
A Novel Framework for Predicting and Managing Comorbid Diseases using Neutrosophic Logic and Machine Learning
2017
International Journal of Computer Applications
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 framework using Artificial Neural Network whose inference mechanism is driven by Neutrosophic logic, all being mechanism employed in soft computing so as to ensure intelligent ...
Precondition B-This contains all relevant data/features for presented disease (Precondition B only). ...
The appropriate features designated as precondition A, Precondition B and Precondition C are described as : Precondition A-This contains all relevant data/features for the presented disease (Precondition ...
doi:10.5120/ijca2017915516
fatcat:vvrbobjnwfekno7hsjuf2rbhjy
LEARNING BY EXPERIMENTATION
[chapter]
1990
Machine 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 2017; you can also visit the original URL.
The file type is application/pdf.
If the environment is too complex or very dynamic, goal-driven learning with reactive feedback becomes a necessity. ...
Thus, experimentation is demand-driven and exploits both the internal state of the planner and any external feedback received. ...
LIVE acquires new operators and refines old ones by interacting with the environment in order to formulate indirectly observable features of objects in the domain, and uses these features in creating new ...
doi:10.1016/b978-0-08-051055-2.50013-4
fatcat:5vaam6i6drgf3ll6mqqafxp7xa
A common framework for learning causality
2018
Progress in Artificial Intelligence
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.
The study of causal inference aims at uncovering causal dependencies amongst observed data and to come up with automated methods to find such dependencies. ...
of symbolic learning. ...
Another interesting feature of symbolic learning is that the inferred models are easily interpreted and understood by humans. ...
doi:10.1007/s13748-018-0151-y
fatcat:btpy6nx4ljgx7k2xom3jau6vmy
Dopamine, Inference, and Uncertainty
2017
Neural 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 2018; you can also visit the original URL.
The file type is application/pdf.
This account can explain dopamine responses to inferred value in sensory preconditioning, the effects of cue pre-exposure (latent inhibition) and adaptive coding of prediction errors when rewards vary ...
We further postulate that orbitofrontal cortex transforms the stimulus representation through recurrent dynamics, such that a simple error-driven learning rule operating on the transformed representation ...
This probability distribution is updated dynamically using Bayesian inference, and the resulting learning equations retain the important features of earlier dopamine models. ...
doi:10.1162/neco_a_01023
pmid:28957023
fatcat:i7lbzefcqraynhg6r7n77wmoim
Dopamine, Inference, and Uncertainty
[article]
2017
bioRxiv
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 2019; you can also visit the original URL.
The file type is application/pdf.
This account can explain dopamine responses to inferred value in sensory preconditioning, the effects of cue pre-exposure (latent inhibition) and adaptive coding of prediction errors when rewards vary ...
We further postulate that orbitofrontal cortex transforms the stimulus representation through recurrent dynamics, such that a simple error-driven learning rule operating on the transformed representation ...
This probability distribution is updated dynamically using Bayesian inference, and the resulting learning equations retain the important features of earlier dopamine models. ...
doi:10.1101/149849
fatcat:3k5riglaxnea5ad433bwgelyp4
InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
[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.
Other Versions
We build a convolutional neural network with an encoder-decoder structure to model the correspondence from seismic data to subsurface velocity structures. ...
To resolve those issues, we employ machine-learning techniques to solve the full-waveform inversion. ...
Data-Driven Techniques In this paper, we adopt a data-driven approach, which means that we employ machine learning techniques directly to infer the velocity model and that no underlying physics is utilized ...
arXiv:1811.07875v2
fatcat:ohq2xjctz5bq7djz6zsetsd7xi
Midbrain dopamine neurons compute inferred and cached value prediction errors in a common framework
2016
eLife
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.
This is important because much real world behavior – and thus many opportunities for error-driven learning – is based on such predictions. ...
Here, we show that error-signaling rat dopamine neurons respond to the inferred, model-based value of cues that have not been paired with reward and do so in the same framework as they track the putative ...
Rats infer the value of cues during sensory preconditioning. ...
doi:10.7554/elife.13665
pmid:26949249
pmcid:PMC4805544
fatcat:rfgwufwglnee7gbjepbfymlg34
`Next Generation' Reservoir Computing: an Empirical Data-Driven Expression of Dynamical Equations in Time-Stepping Form
[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.
It is shown that the NVAR emulator can be interpreted as a data-driven method used to recover the numerical integration scheme that produced the data. ...
It is also shown that the approach can be extended to produce high-order numerical schemes directly from data. ...
It has a general implication that data-driven methods could overfit the data in the sense that it learns the underlying numerical scheme and generalizes poorly to a dataset that uses other schemes. ...
arXiv:2201.05193v1
fatcat:vgawa2itmnhsba4uf3ao7mdocy
Anytime Bounded Rationality
[chapter]
2015
Lecture Notes in Computer Science
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 2015; you can also visit the original URL.
The file type is application/pdf.
This is even more challenging for life-long learning rational agents as they also have to contend with the varying and growing know-how accumulated from experience. ...
We present a value-driven computational model of anytime bounded rationality robust to variations of both resources and knowledge. ...
ABR is data-driven: a writer (W) creates new jobs upon matching inputs to programs while an antagonist eraser (E) enforces a forgetting strategy to limit memory usage. ...
doi:10.1007/978-3-319-21365-1_13
fatcat:nfireca3ijetpn3ch3n7kcsz4y
« Previous
Showing results 1 — 15 out of 14,514 results