## Introduction

This course introduces the basic concepts and techniques of Artificial Intelligence. Artificial intelligence is the sub- area of computer science devoted to creating software and hardware to get computers to do things that would be considered intelligent as if people did them. Artificial intelligence has had an active and exciting history and is now a reasonably mature area of computer science.

## What you will Learn

✅ Understand the core programming concepts of Python Programming Language

✅ Understand the different options in Data Management in Python Programming Language.

✅ Understand the different machine learning techniques and its application

✅Apply the non-linear model for the new observation predictions and its importance in business.

## Course Overview

This course introduces the basic concepts and techniques of Artificial Intelligence. Artificial intelligence is the sub- area of computer science devoted to creating software and hardware to get computers to do things that would be considered intelligent as if people did them. Artificial intelligence has had an active and exciting history and is now a reasonably mature area of computer science.

## CURRICULUM

#### Topic 1: Python

Python is a powerful high-level, object-oriented programming language. It has wide range of applications from Web development, scientific and mathematical computing. The syntax of the language is clean and length of the code is relatively short. It allows you to think about the problem rather than focusing on the syntax. SQLite is one free lightweight database commonly used by Python programmers to store data. Many highly trafficked websites, such as YouTube, are created using Python.

#### Topic 2: Machine Learning

Machine learning is the science of getting computers to act without being explicitly programmed, instead of writing code, you feed data to the generic algorithm, and it builds logic based on the data given. Machine learning algorithms allow for computers to train on data inputs and use statistical analysis in order to output values that fall within a specific range.

#### Topic 3: Deep Learning

Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised. In deep learning, each level learns to transform its input data into a slightly more abstract and composite representation. Deep learning refers to the number of layers through which the data is transformed.

### Course Curriculum

- 1. Module 1: Basic concepts in python, Calculations in python, Variable assignment, Function, Conditions, Data structures – List, Dictionaries, Numpy array, Slicing, Splicing, Subsetting, Functions, Conditions, Loops, Keys, Values, Datatypes
- 2. Module 2: Statistics / Plotting – Seaborn vs Matplotlib, Univariate analysis – Import from csv, Plot histograms, Distribution, Mean, Data with same mean but different standard deviation, Data with same mean and standard deviation but different kurtosis, Bootstrapping and subsetting – making samples, Mean of sample, Central limit theorem, Plotting, Hypothesis testing, Bivariate analysis- correlation, Scatter plots, Stratified samples, Categorical, Class variable.
- 3. Module 3: Series – Datatypes, Index, Data frame – series to data frame, Reindex, Grouping, Pandas shortcuts, Reading from different sources, Missing data treatment, Merge, Join, Writing to file, Database operations.
- 4. Module 4: Regression- Data Aggregation, Filtering, Lamda functions, Map, Filter, Visualization, Matplotlib, Pyplot, Scatterplot, Histogram, Heatmaps. Regression – Linear, Lasso, Ridge, Variable selection, Forward & Backward regression, Polynomial regression.
- 5. Module 5: Logistics regression, Naïve Bayes.
- 6. Module 6: Unsupervised learning, Distance concepts, Classification, k-nearest, Clustering, k-means, Multidimensional scaling.
- 7. Module 7: Decision Trees, Random Forest, Boosted Trees, Gradient Boosting.
- 1. Module 1: Introduction to Python, Numpy Basics, Pandas Basics
- 2. Module 2: Introduction to Machine Learning, Data Preprocessing, Creating validation rules
- 3. Module 3: Regression
- 4. Module 4: Model representation
- 5. Module 5: Introduction to Decision Tree
- 6. Module 6: Introduction to Random Forest
- 7. Module 7: Introduction to SVM
- 8. Module 8: Introduction to Neural Network
- 9. Module 9 : Introduction to Unsupervised Learning
- 10. Module 10: Introduction to Dimension Reduction
- 11. Module 11: Introduction to Nearest Neighbors
- 1. Module 1: NumPy Crash Course Overview, Pandas Crash Course, Data Viz Crash Course, SciKit Learn Overview
- 2. Module 2: TensorFlow Basic Syntax, TensorFlow Graphs and Placeholders, TF Neural Network
- 3. Module 3: TensorFlow Regression Example, TensorFlow Classification Example, Regression Exercise, Classification Exercise
- 4. Module 4: Regression Exercise Solution, Classification Exercise Solution, Saving and Loading Models, Convolutional Neural Networks
- 5. Module 5: Basic Manual RNN, RNN with TF API, Time Series Exercise, Time Series Exercise Solutions, Word2Vec.ipynb
- 6. Module 6: Simple Autoencoder for PCA, Linear Autoencoder for PCA Exercise, Linear Autoencoder for PCA Exercise Solution, Stacked Autoencoder
- 7. Module 7: Generative Adversarial Networks, Example on GAN