Practical Neural Networks & Deep Learning In R

Artificial Intelligence & Machine Learning for Practical Data Science in R

4.56 (233 reviews)

Udemy

platform

English

language

Data Science

What you will learn

Be Able To Harness The Power Of R For Practical Data Science

Read In Data Into The R Environment From Different Sources & Carry Out Basic Pre-processing Tasks

Master The Theory Of Artificial Neural Networks (ANN)

Implement ANN For Classification & Regression Problems In R

Implement Deep Learning In R

Learn The Usage Of The Powerful H2o Package

Learn The Implementation Of Both ANN & DNN Using The H2o Package Of R Programming Language

Course Gallery

Practical Neural Networks & Deep Learning In R – Screenshot 1 — Screenshot 1 – Practical Neural Networks & Deep Learning In R

Practical Neural Networks & Deep Learning In R – Screenshot 2 — Screenshot 2 – Practical Neural Networks & Deep Learning In R

Practical Neural Networks & Deep Learning In R – Screenshot 3 — Screenshot 3 – Practical Neural Networks & Deep Learning In R

Practical Neural Networks & Deep Learning In R – Screenshot 4 — Screenshot 4 – Practical Neural Networks & Deep Learning In R

Loading charts...

Comidoc Review

Our Verdict

Practical Neural Networks & Deep Learning In R offers a thorough dive into neural networks, deep learning, and various R packages—albeit with room for improved presentation and supplementary information. This course is suitable for intermediate learners looking to bolster their AI/ML skills in R with real-world examples and the helpful H2O package.

What We Liked

Covers a wide range of topics in neural networks, deep learning, and R programming
Instructor demonstrates clear understanding of complex AI/ML concepts
Practical examples using real-world datasets
Comprehensive use of the powerful H2O package for deep learning

Potential Drawbacks

Code provided in course sometimes differs from lecture code, causing confusion
Presentations lack polish—excessive description, occasional silences, errors
Limited coverage on choosing appropriate R packages or hyper-parameter tuning
Some explanations for default parameters and cross-validation would be beneficial