LinkedIn

How I Finally Understood Gradient Descent

For a long time, Gradient Descent felt like one of those Machine Learning concepts I would never fully understand. I saw it as a formula full of symbols, until I ...
Analytics Insight

Machine Learning, Stanford University

Stanford University’s Machine Learning (XCS229) is a 100% online, instructor-led course offered by the Stanford School of Engineering. The program teaches professional students essential machine ...
Nature

Thermodynamic natural gradient descent

With the rise of more sophisticated AI models, the cost of training them is exploding, as world-leading models now cost hundreds of millions of dollars to train. This issue is compounded by the ending ...
Nature

A dual enhanced stochastic gradient descent method with dynamic momentum and step size ...

In modern machine learning, optimization algorithms are crucial; they steer the training process by skillfully navigating through complex, high-dimensional loss landscapes. Among these, stochastic ...
Visual Studio Magazine

Kernel Ridge Regression with Stochastic Gradient Descent Training Using JavaScript

Dr. James McCaffrey presents a complete end-to-end demonstration of the kernel ridge regression technique to predict a single numeric value. The demo uses stochastic gradient descent, one of two ...
Visual Studio Magazine

Kernel Ridge Regression with Stochastic Gradient Descent Training Using C#

Dr. James McCaffrey presents a complete end-to-end demonstration of the kernel ridge regression technique to predict a single numeric value. The demo uses stochastic gradient descent, one of two ...
C&EN

Optimized Gradient Boosting Models for Adaptive Prediction of Uniaxial Compressive Strength ...

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Non-Commercial (NC): Only non-commercial uses of the work are permitted. No ...
Frontiers

Gradient-free training of recurrent neural networks using random perturbations

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter ...
Frontiers

On-manifold projected gradient descent

This study provides a computable, direct, and mathematically rigorous approximation to the differential geometry of class manifolds for high-dimensional data, along with non-linear projections from ...
IEEE

Inverse Design of a Single Wavelength Filter Based on the Gradient Descent Algorithm

Abstract: We propose a nanophotonic device inverse design method based on the gradient descent algorithm. The method is similar to the adjoint method, while the gradient is calculated by the python ...
GitHub

Supervised SNN Based on Gradient Descent in TensorFlow

This repo attempts to proposes a supervised learning algorithm of SNN by using spike sequences with complex spatio-temporal information. We explore an error back ...