Jove
Visualize
Contact Us

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
Classification of Signals01:30

Classification of Signals

759
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
759

You might also read

Related Articles

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

Sort by
Same author

Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks.

Frontiers in neuroscience·2024
Same author

A Bayesian Approach to Recurrence in Neural Networks.

IEEE transactions on pattern analysis and machine intelligence·2020
See all related articles
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: Aug 28, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K

A surrogate gradient spiking baseline for speech command recognition.

Alexandre Bittar1,2, Philip N Garner1

  • 1Idiap Research Institute, Martigny, Switzerland.

Frontiers in Neuroscience
|September 19, 2022
PubMed
Summary
This summary is machine-generated.

Spiking neural networks (SNNs) show promise for AI, especially in speech processing. By combining adaptation, recurrence, and surrogate gradients, SNNs can match artificial neural network (ANN) performance and integrate with deep learning frameworks.

Keywords:
artificial intelligencedeep learningphysiologically plausible modelssignal processingspeech recognitionspiking neuronssurrogate gradient learning

More Related Videos

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

519
Study Design for Navigated Repetitive Transcranial Magnetic Stimulation for Speech Cortical Mapping
09:16

Study Design for Navigated Repetitive Transcranial Magnetic Stimulation for Speech Cortical Mapping

Published on: March 24, 2023

1.6K

Related Experiment Videos

Last Updated: Aug 28, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

519
Study Design for Navigated Repetitive Transcranial Magnetic Stimulation for Speech Cortical Mapping
09:16

Study Design for Navigated Repetitive Transcranial Magnetic Stimulation for Speech Cortical Mapping

Published on: March 24, 2023

1.6K

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Artificial neural networks (ANNs) are foundational to AI but use real-valued neuron responses.
  • Biological neurons operate using spike trains, suggesting potential advantages for spiking neural networks (SNNs).
  • SNNs offer potential representational benefits, particularly for time-series data like speech, but face challenges in training and baseline compatibility.

Purpose of the Study:

  • To review literature on the intersection of ANNs and SNNs.
  • To evaluate SNN architectures for speech command tasks using surrogate gradient methods.
  • To demonstrate the competitive performance and compatibility of SNNs with ANNs.

Main Methods:

  • Literature review focusing on surrogate gradient approaches for SNN training.
  • Development of a speech command task evaluation framework.
  • Assessment of various SNN architectures, emphasizing adaptation, recurrence, and surrogate gradients.

Main Results:

  • Identified effective surrogate gradient approaches for SNN training.
  • Demonstrated that SNNs can achieve competitive performance on speech command tasks.
  • Showcased the compatibility of developed SNN architectures with modern deep learning frameworks.

Conclusions:

  • SNNs, particularly when combined with adaptation, recurrence, and surrogate gradients, are viable alternatives to ANNs for AI tasks.
  • SNNs are well-suited for future AI research, especially in speech processing.
  • SNNs may offer insights into biological neural function.