Python for Deep Learning

1.       Introduction to Python

2.       Basic Installation of Python

3.       Keyboard shortcuts and installing packages

4.       How To Install and work with Jupyter notebook

1.        Introduction to NumPy

1.       Introduction to NumPy and its functions

2.       How to select group of objects from a particular array

3.       Indexing a matrix

4.       Selection techniques

5.       Input output options and saving files

2.       Hands On Lab

1.       Numpy lab exercises

2.       Codes and Dataset The code below is used in all the lessons above)

3.       Introduction to Numpy.ipynb

4.       Assignments This assignment has questions to be answered with blank places below the questions)

5.       Numpy Lab Exercise.ipynb

6.       Solution This is a Jupyter notebook with the solutions to the above numpy assignment)

7.       Numpy Lab Exercise – Solutions.ipynb

1.       NumPy vs. pandas package

2.       Functionalities using pandas

3.       Pandas data frames and indexing

4.       Indexing in depth

5.       Deal missing data and group-by options

6.       Merging similar to sql logic

7.       Basic operations in pandas

8.       How to read dataframe from external sources

9.       Pandas_Basic.ipynb (This is the jupyter notebook used in all the video lessons above)

10.   Assignment There are two assignment with the respective datasets and jupyter notebooks below)

11.   Automobile.csv

12.   Pandas Lab Exercise (kaggle automobile dataset).ipynb (assignment 1)

13.   games.csv

14.   Pandas Lab Exercise (Kaggle Games Dataset).ipynb (assignment 2)

15.   Solution The videos and jupyter notebooks below are the solutions to the above assignments)

Hands On Lab

1.       Pandas lab exercises

2.       Pandas Lab Exercise (kaggle automobile dataset) – Solutions.ipynb

3.       Pandas lab exercise with visualization technique_Part 1

4.       Pandas Lab Exercise (Kaggle Games Dataset)- Solutions-1.ipynb

1.       User Defined Functions

2.       Special Functions – Lambda Function

3.       Class and Object

4.       Codes and Datasets (The jupyter notebook below is used in the above video lessons)

5.       Python_functions_Class.ipynb

1.       Visualisation using matplotlib

1.       Introduction to Matplotlib

2.       matplotlib.ipynb

2.       Introduction to sci-kit learn

1.       Introduction to Scikit-Learn

2.       Scikitlearn.pdf

1.       Introduction to probability

2.       Types of Probability and Types of events

3.       Addition Rules

4.       Mulltiplication Rule and Conditional Probability

5.       Marginal Probability

6.       Probability.pdf

1.       How much of Math is required for deep learning

2.       Line Concept

3.       Lines, Planes, and Hyperplanes

4.       Vector algebra_Magnitude and direction

5.       Vector algebra_Vector Operations

6.       Hands On

7.       Vector lab exercises

8.       Basic_Algebra.ipynb

9.       Matrices

1.       Introduction to Functions

2.       Differential of a function

3.       Maxima and Minima of a function

4.       Chain Rule

5.       Maxima and Minima application in machine learning

This is an interesting experiment made by Google. You can draw an object and make AI to guess what it is? Neural networks at work !”

•       “AI Experiments (First residency) – https://experiments.withgoogle.com/collection/ai

The below article by skymind is very interesting. It showcases the entire basics of neural networks and gives an introduction to Neural networks”

•       “Neural Network Definition (First residency) – https://skymind.ai/wiki/neural-network#define

Moments is a research project in development by the MIT-IBM Watson AI Lab. Have a check !

•       “Moments in Time – http://moments.csail.mit.edu/“

•       “Deep Learning – Concepts” – https://devblogs.nvidia.com/deep-learning-nutshell-core-concepts/

The below article by Dren Etzion demystifies the myth that “”Deep Learning is not voodoo magic. It is just pure math at work !

•       Deep Learning Isn’t a Dangerous Magic Genie. It’s Just Math – https://www.wired.com/2016/06/deep-learning-isnt-dangerous-magic-genie-just-math/“

The below article by Jesse Moore delves deep into the misconceptions of deep learning

•       Deep Misconceptions About Deep Learning – https://towardsdatascience.com/deep-misconceptions-about-deep-learning-f26c41faceec“