about
Validation and refinement of gene-regulatory pathways on a network of physical interactionsAutomated discovery of functional generality of human gene expression programsK-ary clustering with optimal leaf ordering for gene expression data.Continuous representations of time-series gene expression data.Combining location and expression data for principled discovery of genetic regulatory network models.Comparing the continuous representation of time-series expression profiles to identify differentially expressed genesLineage-based identification of cellular states and expression programs.A synergistic DNA logic predicts genome-wide chromatin accessibility.Discovery of directional and nondirectional pioneer transcription factors by modeling DNase profile magnitude and shape.Prediction of Organic Reaction Outcomes Using Machine Learning.Bayesian network approach to cell signaling pathway modeling.Predicting Organic Reaction Outcomes with Weisfeiler-Lehman NetworkComputational discovery of gene modules and regulatory networks.Local Aggregative GamesStyle Transfer from Non-Parallel Text by Cross-AlignmentModeling the combinatorial functions of multiple transcription factors.Learning Tree Structured Potential GamesConvolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction.Semi-supervised analysis of gene expression profiles for lineage-specific development in the Caenorhabditis elegans embryo.Physical network models.Special Issue on the Fifth European Workshop on Probabilistic Graphical Models (PGM-2010)Towards Robust Interpretability with Self-Explaining Neural NetworksA graph-convolutional neural network model for the prediction of chemical reactivity.Modeling Persistent Trends in DistributionsTight Certificates of Adversarial Robustness for Randomly Smoothed ClassifiersDirect Optimization through arg max for Discrete Variational Auto-EncoderSolving graph compression via optimal transportA Game Theoretic Approach to Class-wise Selective RationalizationGenerative Models for Graph-Based Protein DesignConvergence of Stochastic Iterative Dynamic Programming AlgorithmsReinforcement Learning Algorithm for Partially Observable Markov Decision ProblemsReinforcement Learning with Soft State AggregationFast Learning by Bounding Likelihoods in Sigmoid Type Belief NetworksPrincipal Differences Analysis: Interpretable Characterization of Differences between DistributionsFrom random walks to distances on unweighted graphsControlling privacy in recommender systemsOn Sampling from the Gibbs Distribution with Random Maximum A-Posteriori PerturbationsLearning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss FunctionsConvergence Rate Analysis of MAP Coordinate Minimization AlgorithmsMore data means less inference: A pseudo-max approach to structured learning
P50
Q24812723-10CCEC3C-0897-439B-8F20-CECB73FF8A12Q28469275-7732522F-0DA0-4CDD-B0A9-D92C831FD982Q30802296-F427AA45-CCA3-477E-A3BC-794286C633F7Q30820114-AE3A9551-270E-46FF-9430-D543B961FCD8Q32072995-B896C529-132C-4A4D-A0FF-883C89CBD6C9Q35917535-7AED74B7-1200-405C-ACAD-91C254316D3BQ36022103-4213A9E1-E9DF-4937-B474-61F29EF97798Q36085119-541D7E38-808F-4119-81ED-B85BB2E8B0DCQ37633701-2386F26F-DB16-48E6-B0BF-5BAD897CE3D9Q42243554-1BFE3369-9B75-4CEA-8AA2-E640FF8CE76CQ44123846-4B094F75-2D7A-4F95-BCFD-8B04DC9EF0D8Q44548939-21862133-F5A5-4A7A-A2D3-6F9512568883Q44615395-5C791895-661B-45D4-A2DF-BD4E852098E3Q44651545-6241E298-8CD2-4A15-BDF5-D0AAF1A0FEE4Q44653670-F78CCCAD-D028-4B80-B960-EFF8D95A8EA2Q46037036-65A4C08C-58D3-4E86-B4C2-DC39A4E940B8Q46993782-C8C01011-E6AA-413E-9032-484FFB93CD5DQ47770444-76643F29-FFBA-44D6-A175-99390CBA477EQ48437426-CAE5923D-2C02-4A14-9FCD-571B06AD7061Q51992781-378CFC15-460B-4B48-95B2-16D8966DF834Q58935817-6778FDCC-A452-47E1-B9D6-5A54191F6D91Q59482710-324539D4-7CEC-4145-B160-721779843193Q60342813-E8F8C44D-D680-4923-9507-656F39E18E96Q62488892-A7750DA5-7BB1-4A60-872A-B71BD5044637Q76470925-929316BB-C07D-4870-8B5A-00FC4B0E2E91Q76471237-3A77B731-5BB9-4C15-9554-8C44796BC135Q76472040-51F719DD-B372-4B51-8647-303D0D398859Q76472496-A29A6906-67CD-45D5-9AE0-05B7E0CF87DEQ76474136-D810999B-7DF9-4C81-8B2A-37952372E107Q77617153-46696AD0-C6AA-4A30-BDB6-E27CB7CA3F68Q77617632-7035B4E6-DAEC-4ABC-99AE-45D94B68CF5FQ77617637-09272F3C-AC8C-417E-B3FE-546F8E504BBDQ77618781-D8AB674A-1746-4C23-8314-E39A4B4B8383Q77623417-8B5AE9B3-8118-4F86-A962-9ACD8C4ADBB9Q77624013-79EC7B5B-7CB4-445D-8001-71D98A7DEF69Q77652639-4DB04FCA-7EE0-4AF6-918E-CACCDB02A65DQ77655366-BF8E83BF-1D67-4B22-A8F6-E5724741FC6DQ77655586-FF69B629-4FAB-46FD-B21B-4F3C4044D07AQ77660235-F9041B57-D010-4F38-89BA-8F92A1D4F5D8Q77667722-B11A3FE2-EE50-4672-B972-7DE2A9C0C5A7
P50
description
computer scientist, Massachusetts Institute of Technology
@en
wetenschapper
@nl
name
Tommi S. Jaakkola
@ast
Tommi S. Jaakkola
@da
Tommi S. Jaakkola
@de
Tommi S. Jaakkola
@en
Tommi S. Jaakkola
@fo
Tommi S. Jaakkola
@fr
Tommi S. Jaakkola
@is
Tommi S. Jaakkola
@kl
Tommi S. Jaakkola
@nb
Tommi S. Jaakkola
@nl
type
label
Tommi S. Jaakkola
@ast
Tommi S. Jaakkola
@da
Tommi S. Jaakkola
@de
Tommi S. Jaakkola
@en
Tommi S. Jaakkola
@fo
Tommi S. Jaakkola
@fr
Tommi S. Jaakkola
@is
Tommi S. Jaakkola
@kl
Tommi S. Jaakkola
@nb
Tommi S. Jaakkola
@nl
altLabel
Tommi Jaakkola
@da
Tommi Jaakkola
@de
Tommi Jaakkola
@en
prefLabel
Tommi S. Jaakkola
@ast
Tommi S. Jaakkola
@da
Tommi S. Jaakkola
@de
Tommi S. Jaakkola
@en
Tommi S. Jaakkola
@fo
Tommi S. Jaakkola
@fr
Tommi S. Jaakkola
@is
Tommi S. Jaakkola
@kl
Tommi S. Jaakkola
@nb
Tommi S. Jaakkola
@nl
P214
P244
P1960
Ao4gtsYAAAAJ
P21
P213
0000 0000 4238 9211
P214
P244
no2001072932
P2456
j/TommiJaakkola
P31
P496
0000-0002-2199-0379
P7859
lccn-no2001072932