MFaiqKhan/Deep-Learning-BWF-FaiqKhan

Bytewise Fellowship Tasks repository , Track : Deep Learning

This Repository Follows the 3 months of Fellowship tasks given by Bytewise Deep-learning FellowShip

Week 01:

• [Task-01] Starting With Git Branching and Merging
• [Task-02] Remote Repositories in Git
• [Task-03] Kicking of with Python
• [Task-04] Lists - Loops - Tuples

Week 02:

• [Task-05] Enumerate - Sets - TimingYourCode - Conditionals - UserInput
• [Task-06] Dictionaries - Dict Methods - Key Values - Looping in Dict - Modifying in Dict
• [Task-07] Functions in Python - DocStrings - Passing Arguments to Functions - Returning Values - Arbitrary Number of Arguments - Don't Repeat Yourself (DRY)
• [Task-08] Classes - Inheritance
• [Task-09] File Reading & Writing, Try Except & Finally

Week 03:

• [Task-10] Introduction to Numpy, Numpy arrays - Single , Multi Dimensions, Arithmetic Operations
• [Task-11] Linear Alegbra with Numpy, Statistical Functions with Numpy
• [Task-12] Broadcasting in Numpy Array
• [Task-13] Introduction to Pandas, Pandas Series, Pandas DataFrames
• [Task-14] Loading Data with Pandas, read_csv(), read_json(), read_excel(), read_sql()

Week 04:

• [Task-15] Handling Missing Data, Filling and Replacing Values, Removing Duplicates, Detecting and Removing Outliers
• [Task-16] Combining and Merging Datasets, Reshaping Data
• [Data-Project-First Project] Data Project - Data Cleaning - Use of Pandas - Matplotlib - Visualization of Data

Week 05:

• [Task-17] KNN Classifier Using Scikit-Learn
• [Task-18] Naïve Bayes Implementation, Decision Tree Implementation

Week 06:

• [Task-19] Introduction to Deep Learning, Building Block of Deep Learning, A look on Neural Network, Tensor Operations
• [Task-20] Introduction to Keras, Example Projects on Classification and Regression

Week 07:

• [Task-21] ["Baat Cheet, discussion, and reporting, Virtual Meetin ONLY"]
• [Task-22] Supervised, Unsupervised, Self-Supervised, and Reinforcement Learning
• [Task-23] Dataset Loading and Understanding Training, Validation and Test Sets