Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 15, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Tensor deep stacking networks.

Brian Hutchinson1, Li Deng, Dong Yu

  • 1Department of Electrical Engineering, University of Washington, Seattle, WA 98105, USA. brianhutchinson@ee.washington.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 26, 2012
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Deep Learning-Guided Reverse Translation Enhances Soluble Expression of Recombinant Proteins in <i>Escherichia coli</i>.

International journal of molecular sciences·2026
Same author

Aharonov-Bohm Beating Induced by Coexisting Topological Surface States and 2DEG in Sb-Doped Bi<sub>2</sub>Se<sub>3</sub> Nanowires.

Nano letters·2026
Same author

Correlation between febrile seizures and cytokines in children: a retrospective study.

Brain & development·2026
Same author

Interplay between noise and higher-order interactions in the stochastic Kuramoto model: From enhancement to explosive transitions.

Physical review. E·2026
Same author

Oral liposomal co-delivery of ultrasmall ceria and 5-aminosalicylic acid alleviates DSS colitis <i>via</i> ROS scavenging and microbiome remodeling.

Journal of materials chemistry. B·2026
Same author

The most common bone tumors of the upper extremity in childhood and adolescence and their treatment: a review of the current literature.

EFORT open reviews·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

A new deep learning model, the tensor deep stacking network (T-DSN), effectively processes complex data. This novel architecture achieves low error rates in tasks like handwritten digit and speech recognition.

Area of Science:

  • Machine Learning
  • Deep Learning Architectures
  • Pattern Recognition

Background:

  • Traditional deep learning models face challenges with higher-order statistics.
  • Efficient training algorithms are crucial for large-scale datasets.

Purpose of the Study:

  • Introduce the tensor deep stacking network (T-DSN), a novel deep architecture.
  • Develop an efficient learning algorithm for the T-DSN.
  • Evaluate the T-DSN's performance on diverse, large-scale tasks.

Main Methods:

  • The T-DSN utilizes stacked blocks with bilinear mappings and weight tensors to capture higher-order statistics.
  • A novel learning algorithm shifts parameter estimation to a convex subproblem with a closed-form solution.
  • An efficient parallel implementation on CPU clusters was used for training.

Related Experiment Videos

Last Updated: May 15, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Main Results:

  • The T-DSN demonstrated consistent effectiveness across handwritten digit recognition (MNIST), and speech tasks (TIMIT, WSJ0).
  • Key factors contributing to low error rates include T-DSN depth, hidden layer symmetry, the learning algorithm, and a softmax output layer.
  • The model achieved low error rates on datasets ranging from 60k to 5.2 million samples.

Conclusions:

  • The tensor deep stacking network (T-DSN) is a powerful deep learning architecture.
  • The developed learning algorithm and architectural features enable high performance on large-scale pattern recognition tasks.
  • The T-DSN shows significant promise for applications requiring the analysis of complex, high-dimensional data.