Representaciones del aprendizaje reutilizando los gradientes de la retropropagacion

12/06/2020
by   Roberto Reyes-Ochoa, et al.
0

This work proposes an algorithm for taking advantage of backpropagation gradients to determine feature importance at different stages of training. Additionally, we propose a way to represent the learning process qualitatively. Experiments were performed over the Wisconsin cancer dataset provided by sklearn, and results showed an interesting convergence of the so called "learning gradients" towards the most important features. — Este trabajo propone el algoritmo de gradientes de aprendizaje para encontrar significado en las entradas de una red neuronal. Ademas, se propone una manera de evaluarlas por orden de importancia y representar el proceso de aprendizaje a traves de las etapas de entrenamiento. Los resultados obtenidos utilizan como referencia el conjunto de datos acerca de tumores malignos y benignos en Wisconsin. Esta referencia sirvio para detectar un patron en las variables mas importantes del modelo gracias, asi como su evolucion temporal.

READ FULL TEXT

page 7

page 9

research
06/13/2018

Apuntes de Redes Neuronales Artificiales

These handouts are designed for people who is just starting involved wit...
research
09/13/2022

Optimization without Backpropagation

Forward gradients have been recently introduced to bypass backpropagatio...
research
11/08/2016

Gradients of Counterfactuals

Gradients have been used to quantify feature importance in machine learn...
research
08/14/2022

Gradient Mask: Lateral Inhibition Mechanism Improves Performance in Artificial Neural Networks

Lateral inhibitory connections have been observed in the cortex of the b...
research
03/31/2022

Perceptual Contrast Stretching on Target Feature for Speech Enhancement

Speech enhancement (SE) performance has improved considerably since the ...
research
06/02/2018

Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition

Spatial and temporal features are two key and complementary information ...
research
12/22/2017

Benchmarking Decoupled Neural Interfaces with Synthetic Gradients

Artifical Neural Network are a particular class of learning system model...

Please sign up or login with your details

Forgot password? Click here to reset