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
SCORES: Shape Composition with Recursive Substructure Priors
[article]
2018
arXiv
pre-print
Preserved Fulltext
SCORES therefore learns a hierarchical substructure shape prior based on per-node losses. ...
We introduce SCORES, a recursive neural network for shape composition. Our network takes as input sets of parts from two or more source 3D shapes and a rough initial placement of the parts. ...
The parts in each test shape were randomly partitioned into groups, which will be mixed and matched to test structure SCORES: Shape Composition with Recursive Substructure Priors • 1:9 Airplane 215 ...
arXiv:1809.05398v1
fatcat:wchwdrv6kjeironmqk6j2aadqy
Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion
[chapter]
2008
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 2017; you can also visit the original URL.
The file type is application/pdf.
We show that the resulting model is comparable with (or better than) alternative methods. ...
We describe a new method for unsupervised structure learning of a hierarchical compositional model (HCM) for deformable objects. ...
Acknowledgements We gratefully acknowledge support from the National Science Foundation with NSF grant number 0413214 and from the W.M. Keck Foundation. ...
doi:10.1007/978-3-540-88688-4_56
fatcat:2wzvj5hocjgojedfmpqmeapdii
PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories
[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
To learn these shared substructures, we learn multi-resolution patch priors across all train categories, which are then associated to input partial shape observations by attention across the patch priors ...
inefficient learning process, particularly for general applications with unseen categories. ...
In summary, our contributions are: • We propose generalizable 3D shape priors by learning patch-based priors that characterize shared local substructures that can be associated with input observations ...
arXiv:2206.04916v2
fatcat:ikaaz3r5srahhkky5xlfs4mzpy
Jet SIFT-ing: a new scale-invariant jet clustering algorithm for the substructure era
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
The clustering measure history facilitates high-performance substructure tagging, which we quantify with the aid of supervised machine learning. ...
These properties suggest that SIFT may prove to be a useful tool for the continuing study of jet substructure. ...
The work of AJL was supported in part by the UC Southern California Hub, with funding from the UC National Laboratories division of the University of California Office of the President. ...
arXiv:2302.08609v1
fatcat:itlw7qs75jcz3h2h2jzzujv6xy
QCD-Aware Recursive Neural Networks for Jet Physics
[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 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our approach works directly with the four-momenta of a variable-length set of particles, and the jet-based tree structure varies on an event-by-event basis. ...
In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. ...
In particular, this recursive neural network (RNN) embeds a binary tree of varying shape and size into a vector of fixed size. ...
arXiv:1702.00748v2
fatcat:qspnz3sqajhodfkxvoqcueokai
QCD-aware recursive neural networks for jet physics
2019
Journal of High Energy Physics
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.
The network is therefore given the 4-momenta without any loss of information, in a way that also captures substructures, as motivated by physical theory. ...
This event-by-event adaptive structure can be contrasted with the 'recurrent' networks that operate purely on sequences (see e.g., [15] ). ...
In particular, this recursive neural network (RNN) embeds a binary tree of varying shape and size into a vector of fixed size. ...
doi:10.1007/jhep01(2019)057
fatcat:bdzapyd2undjzbvkrztgaopjs4
Fine-scale Population Structure and Demographic History of Han Chinese Inferred from Haplotype Network of 111,000 Genomes
[article]
2020
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 2020; you can also visit the original URL.
The file type is application/pdf.
Han Chinese is the most populated ethnic group across the globe with a comprehensive substructure that resembles its cultural diversification. ...
The composition shifts of the native and current residents of four major metropolitans (Beijing, Shanghai, Guangzhou, and Shenzhen) imply a rapidly vanished genetic barrier between subpopulations. ...
For 337 the detection of population substructures recursively, we retained the edges corresponding to 338 a total IBD ≥ 3 cM and applied the Louvain method for the hierarchical clustering (Blondel et ...
doi:10.1101/2020.07.03.166413
fatcat:b3g6l2xjivevvj52ors44vblpm
Development and Applications of Decision Trees
[chapter]
2002
Expert Systems
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.
For example, for the attribute Shape we may have a test with three outcomes {Polygon, Finding the cut that gives the test with the best gain-ratio score for a given treestructured attribute is a rather ...
Starting with the single-attribute test that gives the best possible score, they add each time the single-attribute test that leads to the best improvement in the score, and so on, stopping when the improvement ...
doi:10.1016/b978-012443880-4/50047-8
fatcat:bofagvwzffceldyaca4uqmz434
An In Silico Model for Interpreting Polypharmacology in Drug–Target Networks
[chapter]
2013
Msphere
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.
, implying that the obtained substructure pairs are indispensable components for interpreting polypharmacology. ...
This idea motivates us to build an in silico approach of finding significant substructure patterns from drug-target (molecular graph-amino acid sequence) pairs. ...
atom types except hydrogens and edges are labeled with bond types.3) Drug substructures and target substructures mean connected subgraphs and consecutive subsequences, respectively.4) The support of a ...
doi:10.1007/978-1-62703-342-8_5
pmid:23568464
fatcat:xgx63rrg6ff5zciqpp35w62bmu
Computational Analysis of Conserved RNA Secondary Structure in Transcriptomes and Genomes
2014
Annual Review of Biophysics
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.
I discuss prospects for improving computational methods for analyzing and identifying functional RNAs, with a focus on detecting signatures of conserved RNA secondary structure. ...
At every step of the dynamic programming recursion that adds base i to a growing substructure, depending on whether i is unpaired or paired in that substructure term in the recursion, the appropriate log ...
effect on RNA structure calculations (127)), and homogenize conservation and GC% composition across a window that might encompass a local region of high GC% or high conservation that tends to score highly ...
doi:10.1146/annurev-biophys-051013-022950
pmid:24895857
pmcid:PMC5541781
fatcat:wo4bp7jdlzd4nirxotmqog6azm
Bridging protein local structures and protein functions
2008
Amino Acids
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.
In particular, we emphasize the newly developed structure-based methods, which are able to identify locally structural motifs and reveal their relationship with protein functions. ...
We can simply catalog the types of methods used to identify the local structures as follows: methods to detect profiles of sequences with special local shapes, and methods to detect the substructures with ...
Since the concept of PseAA composition was introduced, various PseAA composition approaches have been developed, all with the aim of improving the prediction quality of protein attributes (Gao et al. ...
doi:10.1007/s00726-008-0088-8
pmid:18421562
fatcat:micrifjcrfetnafnm4fx45ouom
Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space
2020
Heliyon
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.
First, we collect assay data for 65 target human proteins known to interact with the SARS-CoV-2 proteins, including the ACE2 receptor. ...
Including cross-validation with the recursive feature elimination (RFE) partitions the training data into multiple folds. ...
In some cases, enriched substructures were apparent among known ligands, with slight variation in the substructure based on the sensitivity to the targets, suggesting physicochemical features may be relevant ...
doi:10.1016/j.heliyon.2020.e04639
pmid:32802980
pmcid:PMC7409807
fatcat:bmuqbkxuube6vh6jvwofqoklpe
Secondary structure alone is generally not statistically significant for the detection of noncoding RNAs
2000
Bioinformatics
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 2004; you can also visit the original URL.
The file type is application/pdf.
for noncoding RNAs are still usually indistinguishable from noise, especially when certain statistical artifacts resulting from local base-composition inhomogeneity are taken into account. ...
For the thermodynamic implementation (which evaluates statistical significance by doing Monte Carlo shuffling in fixed-length sequence windows, thus eliminating the base-composition effect) the signals ...
As expected, the base-composition model retains most of the scoring shape after the shuffling-after all, base composition contains no structural information. ...
doi:10.1093/bioinformatics/16.7.583
pmid:11038329
fatcat:ppdhf54obvf4lp2yweiwo7bq54
GRAINS: Generative Recursive Autoencoders for INdoor Scenes
[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
, and their relative positioning with respect to other objects in the hierarchy. ...
Hence, our network is not convolutional; it is a recursive neural network or RvNN. ...
Inspired by this work, Li et al. [2017] learn a generative recursive auto-encoder for 3D shape structures. Our work adapts this model for indoor scene generation with non-trivial extensions. ...
arXiv:1807.09193v5
fatcat:ps23v5acxvhvndgluzqyf7shae
Multiscale modeling of developmental processes
1993
Open systems & information dynamics
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.
" or ~recursively generated" artificial neural nets [18] (and elaborated into a connectionist model of biological development [19] ), Despite incorporating all three levels (evolution on genes; development ...
of cells; synapse formation) the model may actuaJ]y be far cheaper to compute with than a comparable search directly in synaptic weight space. ...
By contrast with these systems, the neural nets for visual recognition problems presented in [17] are derived from interpreted grammars which describe the composition and shape of visual objects. ...
doi:10.1007/bf02228972
fatcat:hwpkhk7znzeyfaueayhue2zvui
« Previous
Showing results 1 — 15 out of 706 results