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

Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

532
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
532
Associative Learning01:27

Associative Learning

344
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...
344
Understanding Memory01:19

Understanding Memory

293
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
293
Directional Terms01:14

Directional Terms

8.4K
Directional terms are essential for describing the relative locations of different body structures. For instance, an anatomist might describe one band of tissue as "inferior to" another, or a physician might describe a tumor as "superficial to" a deeper body structure. These terms often use comparative terms in pairs to trace out the relative locations of one body part to another or descriptions of body tissues like the deeper ones from superficially present with reference to...
8.4K
Real-World Application of Classical Conditioning01:15

Real-World Application of Classical Conditioning

550
Classical conditioning not only includes the initial pairing of stimuli but also extends to more complex forms, such as higher-order conditioning. Higher-order conditioning involves creating associations beyond the primary conditioned stimulus, resulting in a chain of conditioned responses.
Higher-order, or second-order, conditioning occurs when a neutral stimulus becomes associated with an already established conditioned stimulus through repeated pairings. For instance, if a dog has been...
550
Parallel Processing01:20

Parallel Processing

150
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
150

You might also read

Related Articles

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

Sort by
Same author

Consensus-Level and Cluster-Adjusted Evaluation of a Large Language Model for Diagnostic Extraction from Musculoskeletal Radiology Reports.

Diagnostics (Basel, Switzerland)·2026
Same author

How Scientific Is Nursing? Answers From A New Characterization of Science.

Nursing philosophy : an international journal for healthcare professionals·2026
Same author

Explainable AI in medicine: challenges of integrating XAI into the future clinical routine.

Frontiers in radiology·2025
Same author

Evaluating the Diagnostic Accuracy of ChatGPT-4.0 for Classifying Multimodal Musculoskeletal Masses: A Comparative Study with Human Raters.

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2025
Same author

Ethics of Sensor-Based Surveillance of People with Dementia in Clinical Practice.

Sensors (Basel, Switzerland)·2025
Same author

ML interpretability: Simple isn't easy.

Studies in history and philosophy of science·2024

Related Experiment Video

Updated: Jun 26, 2025

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

3.9K

The Importance of Understanding Deep Learning.

Tim Räz1, Claus Beisbart1,2

  • 1University of Bern, Institute of Philosophy, Länggassstrasse 49a, 3012 Bern, Switzerland.

Erkenntnis
|May 16, 2024
PubMed
Summary

Deep neural networks (DNNs) are powerful tools in science, but our limited understanding of their inner workings can hinder our ability to truly understand empirical phenomena with them. This paper argues that a strong, explanatory understanding is compromised by this knowledge gap.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

522
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K

Related Experiment Videos

Last Updated: Jun 26, 2025

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

3.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

522
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K

Area of Science:

  • Artificial Intelligence
  • Philosophy of Science
  • Scientific Methodology

Background:

  • Deep neural networks (DNNs) are increasingly utilized in scientific research.
  • A debate exists on whether the "black box" nature of DNNs impedes scientific understanding.
  • Emily Sullivan's argument suggests DNNs can be used for understanding despite their own lack of interpretability.

Purpose of the Study:

  • To critically evaluate Emily Sullivan's argument regarding understanding with DNNs.
  • To determine if the lack of interpretability in DNNs limits their utility for scientific understanding.
  • To differentiate between weak and strong notions of understanding in the context of DNNs.

Main Methods:

  • Philosophical analysis of the concept of "understanding" in science.
  • Argumentative critique of Emily Sullivan's position on DNNs and scientific understanding.
  • Distinction between weak and strong (explanatory) forms of understanding.

Main Results:

  • Sullivan's claim is tenable only under a weak definition of understanding.
  • A strong, explanatory understanding of empirical phenomena using DNNs is indeed limited by the lack of DNN interpretability.
  • The paper refutes the idea that DNNs can provide deep scientific insight without addressing their own opacity.

Conclusions:

  • The interpretability of deep neural networks (DNNs) is crucial for achieving genuine scientific understanding.
  • Relying on DNNs for scientific discovery necessitates addressing their "black box" problem.
  • A strong notion of understanding requires more than predictive accuracy; it demands explanatory insight, which is currently limited by DNN opacity.