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 Concept Videos

Associative Learning01:27

Associative Learning

2.1K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
2.1K
Introduction to Learning01:18

Introduction to Learning

1.6K
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
1.6K
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

9.9K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
9.9K
The Representativeness Heuristic02:13

The Representativeness Heuristic

17.1K
The representative heuristic describes a biased way of thinking, in which you unintentionally stereotype someone or something. For example, you may assume that your professors spend their free time reading books and engaging in intellectual conversation, because the idea of them spending their time playing volleyball or visiting an amusement park does not fit in with your stereotypes of professors.
17.1K
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

2.4K
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
2.4K
State Space Representation01:27

State Space Representation

754
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
754

You might also read

Related Articles

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

Sort by
Same author

Utilization of Computer Classification Methods for Exposure Prediction and Gene Selection in <i>Daphnia magna</i> Toxicogenomics.

Biology·2023
Same author

Fuzzy Cluster-Based Group-Wise Point Set Registration With Quality Assessment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

Age-Related Differences in the Perception of Robotic Referential Gaze in Human-Robot Interaction.

International journal of social robotics·2022
Same author

Are Smart Homes Adequate for Older Adults with Dementia?

Sensors (Basel, Switzerland)·2022
Same author

Predicting mortality among septic patients presenting to the emergency department-a cross sectional analysis using machine learning.

BMC emergency medicine·2021
Same author

Reinforcement Learning Approaches in Social Robotics.

Sensors (Basel, Switzerland)·2021

Related Experiment Video

Updated: Apr 19, 2026

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.1K

Learning feature representations with a cost-relevant sparse autoencoder.

Martin Längkvist1, Amy Loutfi

  • 1School of Science and Technology, Applied Autonomous Sensor Systems, Örebro University, SE-701 82, Örebro, Sweden.

International Journal of Neural Systems
|December 18, 2014
PubMed
Summary
This summary is machine-generated.

This study introduces a novel autoencoder method that improves feature learning from noisy data. By selectively weighting reconstruction errors, it focuses on task-relevant information, enhancing representation quality.

Keywords:
Sparse autoencoderunsupervised feature learningweighted cost function

Related Experiment Videos

Last Updated: Apr 19, 2026

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.1K

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computer Vision

Background:

  • Autoencoders are used for automatic feature learning from unlabeled data.
  • Noisy datasets pose challenges for autoencoders, consuming representational capacity on noise reduction.
  • Existing methods like denoising and contractive autoencoders aim to mitigate noise.

Purpose of the Study:

  • To propose a method that enhances feature learning in autoencoders for noisy datasets.
  • To improve the focus on task-relevant information during the autoencoder training process.
  • To reduce the impact of noisy inputs on learned feature representations.

Main Methods:

  • A novel autoencoder approach is proposed that weights the reconstruction error.
  • This selective attention mechanism reduces the influence of noisy inputs during training.
  • The model is trained and evaluated on publicly available image datasets.

Main Results:

  • The proposed method demonstrates improved feature learning compared to standard sparse autoencoders.
  • Performance is benchmarked against denoising autoencoders and contractive autoencoders.
  • The approach effectively focuses on task-relevant information, leading to better representations.

Conclusions:

  • The proposed weighted reconstruction error method enhances autoencoder performance on noisy data.
  • This technique offers a more efficient way to learn robust feature representations.
  • It provides a valuable alternative for machine learning tasks involving imperfect data.