Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

The Unfolded Protein Response

The Unfolded Protein Response

The ER is the hub of protein synthesis in a cell. It has robust systems to quality control protein folding and also for degradation of terminally misfolded proteins. Under normal conditions, a small proportion of misfolded proteins that cannot be salvaged need to be transported to the cytoplasm by the ER-associated degradation or ERAD pathways. However, if the ERAD cannot handle the misfolded proteins, the cell activates the unfolded protein response or UPR to adjust the protein folding...

Longitudinal Research

Longitudinal Research

Sometimes we want to see how people change over time, as in studies of human development and lifespan. When we test the same group of individuals repeatedly over an extended period of time, we are conducting longitudinal research. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time. For example, we may survey a group of individuals about their dietary habits at age 20, retest them a decade later at age 30, and then again...

Extraction: Advanced Methods

Extraction: Advanced Methods

Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...

Uncertainty: Overview

Uncertainty: Overview

In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.

Principal Moments of Area

Principal Moments of Area

In mechanics, the product of inertia and moments of inertia of area help to calculate the stability and performance of various structures and components. The coordinate transformation relations are used to calculate the moments and products of inertia for an area about the inclined axes. Further, the moments and products of inertia with respect to the principal axes can be determined using the moments and products of inertia about the inclined axes.
The principal moment of inertia axes are the...

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by

Same author

Contrastive Mixture Diffusion Models.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Outlier-Aware Contrastive Learning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

A 28nm Fully Integrated End-to-End Genome Analysis Accelerator for Next-Generation Sequencing.

IEEE transactions on biomedical circuits and systems·2025

Same author

Advancements in Clinical Evaluation and Regulatory Frameworks for AI-Driven Software as a Medical Device (SaMD).

IEEE open journal of engineering in medicine and biology·2024

Same author

Latent Semantic and Disentangled Attention.

IEEE transactions on pattern analysis and machine intelligence·2024

Same author

Hyperspectral signature-band extraction and learning: an example of sugar content prediction of Syzygium samarangense.

Scientific reports·2023

Search research articles

Related Experiment Video

Updated: Mar 6, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Deep Unfolding for Topic Models.

Jen-Tzung Chien, Chao-Hsi Lee

IEEE Transactions on Pattern Analysis and Machine Intelligence

|March 10, 2017

Summary

This summary is machine-generated.

This study introduces deep unfolding inference (DUI) for topic models, enhancing document representation and classification. DUI improves upon variational inference by directly optimizing performance, offering better accuracy and flexibility in unsupervised and supervised learning.

More Related Videos

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Related Experiment Videos

Last Updated: Mar 6, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Area of Science:

Artificial Intelligence
Machine Learning
Natural Language Processing

Background:

Topic models traditionally use variational inference, which can limit representation and classification accuracy.
Variational inference relies on maximizing a lower bound and often ties model parameters, constraining performance.

Purpose of the Study:

To develop unsupervised and supervised deep unfolded topic models for improved document representation and classification.
To overcome limitations of variational inference by directly optimizing end performance criteria.

Main Methods:

Deep unfolding inference (DUI) treats the inference procedure as layer-wise learning in a deep neural network.
Parameters are continuously untied during learning, and end performance is iteratively improved via exponentiated updates.
Deep learning of topic models is achieved through a back-propagation procedure.

Main Results:

Deep unfolded topic models demonstrate superior performance compared to traditional variational inference.
Increasing the number of layers in DUI consistently improved results for both unsupervised and supervised topic models.
DUI offers benefits in deep representation, interpretability, flexible learning, and stochastic modeling.

Conclusions:

Deep unfolding inference (DUI) provides a powerful alternative to variational inference for topic modeling.
DUI enhances document representation and classification accuracy by directly optimizing performance criteria.
The layer-wise learning approach of DUI facilitates deep learning of topic models.