Skip to content

Latest commit

 

History

History
115 lines (62 loc) · 1.59 KB

ML.md

File metadata and controls

115 lines (62 loc) · 1.59 KB

Machine Learning And Deep Learning

This Roadmap is divided into two major parts:

1 .Machine Learning 2. Deep Learning

Prerequisites

Before starting ML or DL you need some basic understnading of underlying topics : --

1.Linear Algebra

2.Calculus

3.Probability

4.Algorithms

5.Python , R or javascript (Depends on you)

Maths for ML

1.Linear Algebra

2.Calculus visual

3.Calculus Theory

4.Linear Algebra EBook

Note : you only need derivatives

5.Probability

Fameworks

1.Keras (Easy for beginners)

2.PyTorch

Learn PyTorch

3.Tensoflow

Learn Tensorflow

Machine Learning

Andrew Ng Coursera this highly recommended.

Andrew Ng Youtube alternative

Machine Learning Lectures- Stanford

Google ML Crash Course

Dive into Machine Learning

Deep Learning How Neural Networks Woks? Neural Network

Start Deep Learning Fast.ai provides you in depth knowledge of Neural Networks in a practical way without going to much detalis of maths behind of it.

Deep Learning Specialization by Coursera This is specialization consist of 5 courses :

1.Neural Networks and Deep Learning

2.Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

3.Structuring Machine Learning Projects

4.Convolutional Neural Networks

5.Sequence Models

NLP 1.Standford CS224N

SVM 1.MIT courseware

Blogs to Follow 1.Towards DataScience

2.christopher olah

3.andrew trask

AI Podcasts-- 1.Lex Fridman

Peoples to follow on Twitter- @ylecun

@rsalakhu

@karpathy

@hugo_larochelle

@goodfellow_ian

@drfeifei

@soumithchintala

@nandodf

@jeffdean