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

Survival Tree01:19

Survival Tree

351
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
351
Classification of Systems-I01:26

Classification of Systems-I

508
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
508
Classification of Systems-II01:31

Classification of Systems-II

436
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
436
How Data are Classified: Categorical Data01:11

How Data are Classified: Categorical Data

42.3K
A variable, usually notated by capital letters such as X and Y, is a characteristic or measurement that can be determined for each member of a population. Data are the actual values of variables. They may be numbers, or they may be words. Datum is a single value.
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
42.3K
Aggregates Classification01:29

Aggregates Classification

919
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
919
Ranks01:02

Ranks

425
Unlike parametric methods, nonparametric statistics are ideal for nominal and ordinal data, requiring fewer assumptions about the population's nature or distribution. This makes nonparametric methods easier to apply and interpret, as they do not depend on parameters like mean or standard deviation. One common approach in nonparametric analysis is to sort data according to a specific criterion. For instance, we might arrange weather data from hottest to coldest days in a month or rank cities...
425

You might also read

Related Articles

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

Sort by
Same author

Multi-modal AI for comprehensive breast cancer prognostication.

Nature communications·2026
Same author

To Compress or Not to Compress-Self-Supervised Learning and Information Theory: A Review.

Entropy (Basel, Switzerland)·2024
Same author

Catalyzing next-generation Artificial Intelligence through NeuroAI.

Nature communications·2023
Same author

Deep learning, reinforcement learning, and world models.

Neural networks : the official journal of the International Neural Network Society·2022
Same author

Inspirational Adversarial Image Generation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

The Mind of a Mouse.

Cell·2020

Related Experiment Videos

A hierarchical loss and its problems when classifying non-hierarchically.

Cinna Wu1, Mark Tygert1, Yann LeCun2

  • 1Facebook, Menlo Park, CA, United States of America.

Plos One
|December 20, 2019
PubMed
Summary
This summary is machine-generated.

New metrics for neural network classification penalize misclassifying a sheepdog as a skyscraper more than a poodle. This hierarchical loss, based on ultrametric trees, offers a more semantically meaningful evaluation of classifier performance.

Related Experiment Videos

Area of Science:

  • Machine Learning
  • Computer Vision
  • Artificial Intelligence

Background:

  • Current classification metrics in neural networks often fail to incorporate a-priori knowledge about class similarity.
  • Existing loss functions do not adequately penalize semantically dissimilar misclassifications, such as confusing a dog breed with an inanimate object.

Purpose of the Study:

  • To define a novel hierarchical loss metric for neural network classification.
  • To develop a metric that penalizes misclassifications based on the semantic hierarchy of classes.

Main Methods:

  • The study defines a new metric based on an ultrametric tree, which organizes classifier classes into a meaningful hierarchy.
  • This metric utilizes an ultrametric distance, ensuring all leaves are equidistant from the root.

Main Results:

  • Numerical experiments indicate that standard stochastic gradient descent training minimizes the proposed hierarchical loss similarly to cross-entropy loss, even without direct optimization.
  • The hierarchical loss is found to be unreliable as a direct objective for standard training methods.

Conclusions:

  • The primary value of the hierarchical loss lies in its utility as a meaningful metric for evaluating classifier success.
  • The developed metric provides a more nuanced assessment of classification performance by considering semantic relationships between classes.