Interpretability of Neural Network With Physiological Mechanisms

@article{Zou2022InterpretabilityON,
  title={Interpretability of Neural Network With Physiological Mechanisms},
  author={An–Min Zou and Zhiyuan Li},
  journal={ArXiv},
  year={2022},
  volume={abs/2203.13262}
}
  • An–Min ZouZhiyuan Li
  • Published 24 March 2022
  • Computer Science
  • ArXiv
— Deep learning continues to be a powerful state-of-art technique that has achieved extraordinary accuracy levels in various domains of regression and classification tasks, including image, signal, and natural language data. The original goal of proposing the neural network model is to improve the understanding of complex human brains using a mathematical approach. However, recent deep learning techniques continue to be difficult to interpret in addition to challenges in explain-ing its… 
View PDF on arXiv

References

SHOWING 1-10 OF 38 REFERENCES

Toward an Integration of Deep Learning and Neuroscience

It is argued that a range of implementations of credit assignment through multiple layers of neurons are compatible with current knowledge of neural circuitry, and that the brain's specialized systems can be interpreted as enabling efficient optimization for specific problem classes.

Backpropagation and the brain

It is argued that the key principles underlying backprop may indeed have a role in brain function and induce neural activities whose differences can be used to locally approximate these signals and hence drive effective learning in deep networks in the brain.

A Comprehensive Survey of Loss Functions in Machine Learning

This paper summarizes and analyzes 31 classical loss functions in machine learning from the aspects of traditional machine learning and deep learning respectively and mainly selects object detection and face recognition to introduces their loss functions.

Estimation of the Scale Parameter of the Selected Gamma Population Under the Entropy Loss Function

Let X 1, X 2,…, X k be k (≥2) independent random variables from gamma populations Π1, Π2,…, Π k with common known shape parameter α and unknown scale parameter θ i , i = 1,2,…,k, respectively. Let X…

The organization of behavior: A neuropsychological theory

Action potential of the motorneuron

The model geometrical factors for the myelinated axon, initial segment and cell body were derived from anatomical measurements, the dendritic tree was represented by its equivalent cylinder, and the current-voltage relations of the membrane were described by a modification of the Hodgkin-Huxley model that fits voltage-clamp data from the motorneuron.

PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS

The background, basic sources of data, concepts, and methodology to be employed in the study of perceptrons are reviewed, and some of the notation to be used in later sections are presented.

Shared and distinct transcriptomic cell types across neocortical areas

This study establishes a combined transcriptomic and projectional taxonomy of cortical cell types from functionally distinct areas of the adult mouse cortex and identifies 133 transcriptomic types of glutamatergic neurons to their long-range projection specificity.

Refractory period of human muscle after the passage of a propagated action potential.

Heuristics and Biases: The Psychology of Intuitive Judgment

A review is presented of the book “Heuristics and Biases: The Psychology of Intuitive Judgment,” edited by Thomas Gilovich, Dale Griffin, and Daniel Kahneman.