# AI News, Why is Genetic Programming not popular in machine learning?

- On Thursday, October 4, 2018
- By Read More

## Why is Genetic Programming not popular in machine learning?

Main advantage of evolutionary technique is its ability to get global optimum in a parallel framework, even as an outsider of the original problem.

Progress in GPU research with availability of digital data, facilitates us to attack relatively difficult machine learning problems (vision, speech, language) in recent years, where dimension of the problem space is very high.

On contrary, automatic differentiation aided gradient based techniques are quite successful in training for high dimensional problems without sticking-up inside a local minimum, as upward slopes in all the dimensions, which is required for local minimum is extremely rare.

- On Monday, September 23, 2019

**Introduction To Gradient Boosting algorithm (simplistic n graphical) - Machine Learning**

In this tutorial, you will learn -What is gradient boosting? Other name of same stuff is Gradient descent -How does it work for 1. Numeric outcome - Regression ...

**Introduction To Optimization: Gradient Based Algorithms**

A conceptual overview of gradient based optimization algorithms. NOTE: Slope equation is mistyped at 2:20, should be delta_y/delta_x. This video is part of an ...

**What is Optimization? + Learning Gradient Descent | Two Minute Papers #82**

Let's talk about what mathematical optimization is, how gradient descent can solve simpler optimization problems, and Google DeepMind's proposed algorithm ...

**Gradient descent algorithm (neural networks) explanation with derivation in Hindi**

The video explains gradient descent algorithm used in machine learning, deep learning with derivation in Hindi. If you need explanation of any other deep ...

**Gradient Descent - Artificial Intelligence for Robotics**

This video is part of an online course, Intro to Artificial Intelligence. Check out the course here:

**Lecture: Multi Dimensional Gradient Methods in Optimization -- Example Part 1 of 2**

Learn the Multi-Dimensional Gradient Method of optimization via an example. Minimize an objective function with two variables (part 1 of 2).

**Natalie Hockham: Machine learning with imbalanced data sets**

Classification algorithms tend to perform poorly when data is skewed towards one class, as is often the case when tackling real-world problems such as fraud ...

**The Evolution of Gradient Descent**

Which optimizer should we use to train our neural network? Tensorflow gives us lots of options, and there are way too many acronyms. We'll go over how the ...

**Lecture 3 | Loss Functions and Optimization**

Lecture 3 continues our discussion of linear classifiers. We introduce the idea of a loss function to quantify our unhappiness with a model's predictions, and ...

**4.3 Gradient-Based Optimization (Part 1)**

Book: Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville.