Artificial Intelligence Engineer

01 : Return of Multi-Armed Bandit

02 : Higher Level Overviw of Reinforcement Learning

03 : Markov Decision Process

04 : Dynamic Programming

05 : Monte Carlo

06 : Temporal Difference Learning

07 : Approximation Methods

08 : Stock trading Project with Reinforcement Learning

01 : Starting with Python

• Why Python Is Hot.
• Choosing the Right Python.
• Tools for Success.
• An excellent, free learning environment.
• Installing Anaconda and VS Code.
• Writing Python in VS Code.
• Choosing your Python interpreter
• Writing some Python code.
• Getting back to VS Code Python
• Using Jupyter Notebook for Coding

02 : Interactive Mode, Getting Help, Writing Apps.

• Using Python Interactive Mode.
• Opening Terminal.
• Getting your Python version .
• Going into the Python Interpreter .
• Entering commands.
• Using Python’s built-in help.
• Exiting interactive help.
• Searching for specific help topics online.
• Lots of free cheat sheets .
• Creating a Python Development Workspace.
• Creating a Folder for your Python Code .
• Typing, Editing, and Debugging Python Code.
• Writing Python code.
• Saving your code.
• Running Python in VS Code.
• Simple debugging.
• The VS Code Python debugger .
• Writing Code in a Jupyter Notebook.
• Creating a folder for Jupyter Notebook.
• Creating and saving a Jupyter notebook.
• Typing and running code in a notebook .
• Adding some Markdown text.
• Saving and opening notebooks.

03 : Python Elements and Syntax.

• The Zen of Python.
• Object-Oriented Programming.
• Indentations Count, Big Time .
• Using Python Modules.
• Syntax for importing modules.
• Using an alias with modules .

04 : Building Your First Python Application.

• Open the Python App File .
• Typing and Using Python Comments.
• Understanding Python Data Types.
• Numbers.
• Words (strings).
• True/false Booleans .
• Doing Work with Python Operators.
• Arithmetic operators
• Comparison operators.
• Boolean operators.
• Creating and Using Variables.
• Creating valid variable names.
• Creating variables in code.
• Manipulating variables.
• Saving your work.
• Running your Python app in VS Code.
• What Syntax Is and Why It Matters.
• Putting Code Together.

UNDERSTANDING PYTHON-BUILDING BLOCKS.

05 : Working with Numbers, Text, and Dates

• Calculating Numbers with Functions.
• Still More Math Functions .
• Formatting Numbers .
• Formatting with f-strings .
• Showing dollar amounts.
• Formatting percent numbers .
• Making multiline format strings .
• Formatting width and alignment.
• Grappling with Weirder Numbers.
• Binary, octal, and hexadecimal numbers.
• Complex numbers.
• Manipulating Strings.
• Concatenating strings.
• Getting the length of a string.
• Working with common string operators.
• Manipulating strings with methods .
• Uncovering Dates and Times.
• Working with dates.
• Working with times.
• Calculating timespans.
• Accounting for Time Zones .
• Working with Time Zones.

06 : Controlling the Action

• Main Operators for Controlling the Action .
• Making Decisions with if.
• Adding else to your if login.
• Handling multiple else’s with elif.
• Ternary operations.
• Repeating a Process with for.
• Looping through numbers in a range .
• Looping through a string.
• Looping through a list.
• Bailing out of a loop .
• Looping with continue
• Nesting loops.
• Looping with while .
• Starting while loops over with continue.
• Breaking while loops with break.

07 : Speeding Along with Lists and Tuples.

• Defining and Using Lists.
• Referencing list items by position.
• Looping through a list
• Seeing whether a list contains an item. . . .
• Getting the length of a list.
• Adding an item to the end of a list.
• Inserting an item into a list .
• Changing an item in a list.
• Combining list
• Removing Removing list items.
• Clearing out a list.
• Counting how many times an item appears in a list .
• Finding an list item’s index.
• Alphabetizing and sorting lists. . . . . .
• Reversing a list.
• Copying a list .
• What’s a Tuple and Who Cares? .
• Working with Sets.

08 : Cruising Massive Data with Dictionaries

• Creating a Data Dictionary.
• Accessing dictionary data.
• Getting the length of a dictionary.
• Seeing whether a key exists in a dictionary
• Getting dictionary data with get().
• Changing the value of a key.
• Adding or changing dictionary data.
• Looping through a Dictionary.
• Data Dictionary Methods.
• Copying a Dictionary.
• Deleting Dictionary Items.
• Using pop() with Data Dictionaries.
• Fun with Multi-Key Dictionaries.
• Using the mysterious fromkeys and setdefault methods.
• Nesting Dictionaries

09 : Wrangling Bigger Chunks of Code

• Creating a Function.
• Commenting a Function.
• Passing Information to a Function.
• Defining optional parameters with defaults.
• Passing multiple values to a function.
• Using keyword arguments (kwargs).
• Passing multiple values in a list.
• Passing in an arbitrary number of arguments .
• Returning Values from Functions.
• Unmasking Anonymous Functions.

10 : Doing Python with Class

• Mastering Classes and Objects.
• Creating a Class.
• How a Class Creates an Instance .
• Giving an Object Its Attributes.
• Creating an instance from a class.
• Changing the value of an attribute.
• Defining attributes with default values .
• Giving a Class Methods.
• Passing parameters to methods.
• Calling a class method by class name .
• Using class variables.
• Using class methods.
• Using static methods .
• Understanding Class Inheritance
• Creating the base (main) class.
• Defining a subclass.
• Overriding a default value from a subclass.
• Adding extra parameters from a subclass.
• Calling a base class method.
• Using the same name twice.

11 : Sidestepping Errors

• Understanding Exceptions
• Handling Errors Gracefully.
• Being Specific about Exceptions.
• Keeping Your App from Crashing.
• Adding an else to the Mix.
• Using try . . . except . . . else . . . finally.
• Raising Your Own Errors

WORKING WITH PYTHON LIBRARIES

12 : Working with External Files

• Understanding Text and Binary Files.
• Opening and Closing Files.
• Reading a File’s Contents.
• Looping through a File.
• Looping with readlines().
• Looping with readline().
• Appending versus overwriting files.
• Using tell() to determine the pointer location.
• Moving the pointer with seek().
• Reading and Copying a Binary File.
• Conquering CSV Files .
• Opening a CSV file.
• Converting strings.
• Converting to integers .
• Converting to date.
• Converting to Boolean
• Converting to floats.
• From CSV to Objects and Dictionaries.
• Importing CSV to Python objects.
• Importing CSV to Python dictionaries.

13 : Juggling JSON Data

• Organizing JSON Data.
• Understanding Serialization .
• Loading Data from JSON Files.
• Converting an Excel date to a JSON date.
• Looping through a keyed JSON file.
• Converting firebase timestamps to Python dates .
• Loading unkeyed JSON from a Python string .
• Loading keyed JSON from a Python string.
• Changing JSON data .
• Removing data from a dictionary.
• Dumping Python Data to JSON.

14 : Interacting with the Internet.

• How the Web Works.
• Understanding the mysterious URL.
• Exposing the HTTP headers.
• Opening a URL from Python .
• Posting to the Web with Python.
• Scraping the Web with Python .
• Parsing part of a page.
• Storing the parsed content
• Saving scraped data to a JSON file .
• Saving scraped data to a CSV file .

15 : Libraries, Packages, and Modules

• Understanding the Python Standard Library .
• Using the dir() function.
• Using the help() function .
• Exploring built-in functions .
• Exploring Python Packages .
• Importing Python Modules .
• Making Your Own Modules.

01 : Vectors, Matrices, and Arrays

• Introduction
• Creating a Vector
• Creating a Matrix
• Creating a Sparse Matrix
• Selecting Elements
• Describing a Matrix
• Applying Operations to Elements
• Finding the Maximum and Minimum Values
• Calculating the Average, Variance, and Standard Deviation
• Reshaping Arrays
• Transposing a Vector or Matrix
• Flattening a Matrix
• Finding the Rank of a Matrix
• Calculating the Determinant
• Getting the Diagonal of a Matrix
• Calculating the Trace of a Matrix
• Finding Eigenvalues and Eigenvectors
• Calculating Dot Products
• Adding and Subtracting Matrices
• Multiplying Matrices
• Inverting a Matrix
• Generating Random Values

02 : Loading Data

• Introduction
• Loading a Sample Dataset
• Creating a Simulated Dataset
• Loading a CSV File
• Loading an Excel File
• Loading a JSON File
• Querying a SQL Database

03 : Data Wrangling

• Introduction
• Creating a Data Frame
• Describing the Data
• Navigating DataFrames
• Selecting Rows Based on Conditionals
• Replacing Values
• Renaming Columns
• Finding the Minimum, Maximum, Sum, Average, and Count
• Finding Unique Values
• Handling Missing Values
• Deleting a Column
• Deleting a Row
• Dropping Duplicate Rows
• Grouping Rows by Values
• Grouping Rows by Time
• Looping Over a Column
• Applying a Function Over All Elements in a Column
• Applying a Function to Groups
• Concatenating DataFrames
• Merging DataFrames

04 : Handling Numerical Data

• Introduction
• Rescaling a Feature
• Standardizing a Feature
• Normalizing Observations
• Generating Polynomial and Interaction Features
• Transforming Features
• Detecting Outliers
• Handling Outliers
• Discretizating Features
• Grouping Observations Using Clustering
• Deleting Observations with Missing Values
• Imputing Missing Values

05 : Handling Categorical Data

• Introduction
• Encoding Nominal Categorical Features
• Encoding Ordinal Categorical Features
• Encoding Dictionaries of Features
• Imputing Missing Class Values
• Handling Imbalanced Classes

06 : Handling Text

• Introduction
• Cleaning Text
• Parsing and Cleaning HTML
• Removing Punctuation
• Tokenizing Text
• Removing Stop Words
• Stemming Words
• Tagging Parts of Speech
• Encoding Text as a Bag of Words
• Weighting Word Importance

07 : Handling Dates and Times

• Introduction
• Converting Strings to Dates
• Handling Time Zones
• Selecting Dates and Times
• Breaking Up Date Data into Multiple Features
• Calculating the Difference Between Dates
• Encoding Days of the Week
• Creating a Lagged Feature
• Using Rolling Time Windows
• Handling Missing Data in Time Series

08 : Handling Images

• Introduction
• Loading Images
• Saving Images
• Resizing Images
• Cropping Images
• Blurring Images
• Sharpening Images
• Enhancing Contrast
• Isolating Colors
• Binarizing Images
• Removing Backgrounds
• Detecting Edges
• Detecting Corners
• Creating Features for Machine Learning
• Encoding Mean Color as a Feature
• Encoding Color Histograms as Features

09 : Dimensionality Reduction Using Feature Extraction

• Introduction
• Reducing Features Using Principal Components
• Reducing Features When Data Is Linearly Inseparable
• Reducing Features by Maximizing Class Separability
• Reducing Features Using Matrix Factorization
• Reducing Features on Sparse Data

10 : Dimensionality Reduction Using Feature Selection

• Introduction
• Thresholding Numerical Feature Variance
• Thresholding Binary Feature Variance
• Handling Highly Correlated Features
• Removing Irrelevant Features for Classification
• Recursively Eliminating Features

11 : Model Evaluation

• Introduction
• Cross-Validating Models
• Creating a Baseline Regression Model
• Creating a Baseline Classification Model
• Evaluating Binary Classifier Predictions
• Evaluating Binary Classifier Thresholds
• Evaluating Multiclass Classifier Predictions
• Visualizing a Classifier’s Performance
• Evaluating Regression Models
• Evaluating Clustering Models
• Creating a Custom Evaluation Metric
• Visualizing the Effect of Training Set Size
• Creating a Text Report of Evaluation Metrics
• Visualizing the Effect of Hyperparameter Values

12 : Model Selection

• Introduction
• Selecting Best Models Using Exhaustive Search
• Selecting Best Models Using Randomized Search
• Selecting Best Models from Multiple Learning Algorithms
• Selecting Best Models When Preprocessing
• Speeding Up Model Selection with Parallelization
• Speeding Up Model Selection Using Algorithm-Specific Methods
• Evaluating Performance After Model Selection

13 : Linear Regression

• Introduction
• Fitting a Line
• Handling Interactive Effects
• Fitting a Nonlinear Relationship
• Reducing Variance with Regularization
• Reducing Features with Lasso Regression

14 :Trees and Forests

• Introduction
• Training a Decision Tree Classifier
• Training a Decision Tree Regressor
• Visualizing a Decision Tree Model
• Training a Random Forest Classifier
• Training a Random Forest Regressor
• Identifying Important Features in Random Forests
• Selecting Important Features in Random Forests
• Handling Imbalanced Classes
• Controlling Tree Size
• Improving Performance Through Boosting
• Evaluating Random Forests with Out-of-Bag Errors

15 : K-Nearest Neighbors.

• Introduction
• Finding an Observation’s Nearest Neighbors
• Creating a K-Nearest Neighbor Classifier
• Identifying the Best Neighborhood Size
• Creating a Radius-Based Nearest Neighbor Classifier

16 : Logistic Regression

• Introduction
• Training a Binary Classifier
• Training a Multiclass Classifier
• Reducing Variance Through Regularization
• Training a Classifier on Very Large Data
• Handling Imbalanced Classes

17 : Support Vector Machines

• Introduction
• Training a Linear Classifier
• Handling Linearly Inseparable Classes Using Kernels
• Creating Predicted Probabilities
• Identifying Support Vectors
• Handling Imbalanced Classes

18 : Naive Bayes

• Introduction
• Training a Classifier for Continuous Features
• Training a Classifier for Discrete and Count Features
• Training a Naive Bayes Classifier for Binary Features
• Calibrating Predicted Probabilities

19 : Clustering

• Introduction
• Clustering Using K-Means
• Speeding Up K-Means Clustering
• Clustering Using Meanshift
• Clustering Using DBSCAN
• Clustering Using Hierarchical Merging

20 : Neural Networks

• Introduction
• Preprocessing Data for Neural Networks
• Designing a Neural Network
• Training a Binary Classifier
• Training a Multiclass Classifier
• Training a Regressor
• Making Predictions
• Visualize Training History
• Reducing Overfitting with Weight Regularization
• Reducing Overfitting with Early Stopping
• Reducing Overfitting with Dropout
• Saving Model Training Progress
• k-Fold Cross-Validating Neural Networks
• Tuning Neural Networks
• Visualizing Neural Networks
• Classifying Images
• Improving Performance with Image Augmentation
• 20.17 Classifying Text

21 : Saving and Loading Trained Models

• Introduction
• Saving and Loading a scikit-learn Model
• Saving and Loading a Keras Model

01 : An Introduction to Data Analysis

Data Analysis

• Knowledge Domains of the Data Analyst
• Computer Science
• Mathematics and Statistics
• Machine Learning and Artificial Intelligence
• Professional Fields of Application

02 : Understanding the Nature of the Data

• When the Data Become Information
• When the Information Becomes Knowledge
• Types of Data

03 : The Data Analysis Process

• Problem Definition
• Data Extraction
• Data Preparation
• Data Exploration/Visualization
• Predictive Modeling
• Model Validation
• Deployment

04 : Quantitative and Qualitative Data Analysis

• Open Data
• Python and Data Analysis

05 : The NumPy Library

• NumPy: A Little History
• The NumPy Installation
• Ndarray: The Heart of the Library
• Create an Array
• Types of Data
• The dtype Option
• Intrinsic Creation of an Array

06 : Basic Operations

• Arithmetic Operators
• The Matrix Product
• Increment and Decrement Operators
• Universal Functions (ufunc)
• Aggregate Functions

07 : Indexing, Slicing, and Iterating

• Indexing
• Slicing
• Iterating an Array

Conditions and Boolean Arrays

Shape Manipulation

08 : Array Manipulation

• Joining Arrays
• Splitting Arrays

09 : General Concepts

• Vectorization
• Broadcasting

Structured Arrays

10 : Reading and Writing Array Data on Files

• Loading and Saving Data in Binary Files
• Reading File with Tabular Data

11: pandas: The Python Data Analysis Library

The pandas Library—An Introduction

• Understanding Exceptions
• Installation from Anaconda
• Installation from PyPI
• Installation on Linux
• Installation from Source
• A Module Repository for Windows

Test Your pandas Installation

Getting Started with pandas

WORKING WITH PYTHON LIBRARIES

12 : Introduction to pandas Data Structures

• The Series
• The DataFrame
• The Index Objects

13 : Other Functionalities on Indexes

• Reindexing
• Dropping
• Arithmetic and Data Alignment

14 : Operations between Data Structures

• Flexible Arithmetic Methods
• Operations between DataFrame and Series

15 : Function Application and Mapping

• Functions by Element
• Functions by Row or Column
• Statistics Functions

Sorting and Ranking

Correlation and Covariance

16 : “Not a Number” Data

• Assigning a NaN Value
• Filtering Out NaN Values
• Filling in NaN Occurrences

17 : Hierarchical Indexing and Leveling

• Reordering and Sorting Levels
• Summary Statistic by Level

Pandas: Reading and Writing Data

I/O API Tools

CSV and Textual Files

18 : Reading Data in CSV or Text Files

• Using RegExp for Parsing TXT Files
• Reading TXT Files into Parts or Partially
• Writing Data in CSV

19 : Reading and Writing HTML Files

• Writing Data in HTML
• Reading Data from an HTML File

Reading Data from XML

20 : Reading and Writing Data on Microsoft Excel Files

• JSON Data
• The Format HDF5

21 : Pickle—Python Object Serialization

• Serialize a Python Object with cPickle
• Pickling with pandas

22 : Interacting with Databases

• Loading and Writing Data with SQLite
• Loading and Writing Data with PostgreSQL

Reading and Writing Data with a NoSQL Database: MongoDB

pandas in Depth: Data Manipulation

23 : Data Preparation

• Merging

24 : Concatenating

• Combining
• Pivoting
• Removing

25 : Data Transformation

• Removing Duplicates
• Mapping

26 : Discretization and Binning

• Detecting and Filtering Outliers

Permutation

27 : String Manipulation

• Built-in Methods for Manipulation of Strings
• Regular Expressions

28 : Data Aggregation

• GroupBy
• A Practical Example
• Hierarchical Grouping

29 : Group Iteration

• Chain of Transformations
• Functions on Groups

Advanced Data Aggregation

Data Visualization with matplotlib

The matplotlib Library

Installation

IPython and IPython QtConsole

30 : matplotlib Architecture

• Backend Layer
• Artist Layer
• Scripting Layer (pyplot)
• pylab and pyplot

31 : pyplot

• A Simple Interactive Chart
• Set the Properties of the Plot
• matplotlib and NumPy

32 : Using the kwargs

• Working with Multiple Figures and Axes

33 : Adding Further Elements to the Chart

• Adding Text
• Adding a Grid
• Adding a Legend

34 : Saving Your Charts

• Saving the Code
• Converting Your Session as an HTML File
• Saving Your Chart Directly as an Image

Handling Date Values

Chart Typology

35 : Line Chart

• Line Charts with pandas

Histogram

36 : Bar Chart

• Horizontal Bar Chart
• Multiserial Bar Chart
• Multiseries Bar Chart with pandas DataFrame
• Multiseries Stacked Bar Charts
• Stacked Bar Charts with pandas DataFrame
• Other Bar Chart Representations

37 : Pie Charts

• Pie Charts with pandas DataFrame

38 : Advanced Charts

• Contour Plot
• Polar Chart

39 : mplot3d

• 3D Surfaces
• Scatter Plot in 3D
• Bar Chart 3D

40 : Multi-Panel Plots

• Display Subplots within Other Subplots
• Grids of Subplots

01 : What is Deep learning?

• What is Deep learning?
• Deep learning Process
• Classification of Neural Networks
• Types of Deep Learning Networks
• Feed-forward neural networks
• Recurrent neural networks (RNNs)
• Convolutional neural networks (CNN)

02 : Machine Learning vs Deep Learning

• What is AI?
• What is ML?
• What is Deep Learning?
• Machine Learning Process
• Deep Learning Process
• Automate Feature Extraction using DL
• Difference between Machine Learning and Deep Learning
• When to use ML or DL?

03 : What is TensorFlow?

• What is TensorFlow?
• History of TensorFlow
• TensorFlow Architecture
• Where can Tensorflow run?
• Introduction to Components of TensorFlow
• Why is TensorFlow popular?
• List of Prominent Algorithms supported by TensorFlow

04 : Comparison of Deep Learning Libraries

• 8 Best Deep learning Libraries /Framework
• MICROSOFT COGNITIVE TOOLKIT(CNTK)
• TenserFlow Vs Theano Vs Torch Vs Keras Vs infer.net Vs CNTK Vs MXNet Vs Caffe: Key Differences

05 : How to Download and Install TensorFlow Windows and Mac

• TensorFlow Versions
• Install Anaconda
• Create .yml file to install Tensorflow and dependencies
• Launch Jupyter Notebook
• Jupyter with the main conda environment

06 : Jupyter Notebook Tutorial

• What is Jupyter Notebook?
• Jupyter Notebook App
• How to use Jupyter

07 : Tensorflow on AWS

• PART 1: Set up a key pair
• PART 2: Set up a security group
• Launch your instance (Windows users)
• Part 4: Install Docker
• Part 5: Install Jupyter
• Part 6: Close connection

08 : TensorFlow Basics: Tensor, Shape, Type, Graph, Sessions & Operators

• What is a Tensor?
• Representation of a Tensor
• Types of Tensor
• Shape of tensor
• Type of data
• Creating operator
• Variables

09 : Tensorboard: Graph Visualization with Example

10 : Scikit-Lear

• What is Scikit-learn?
• Download and Install scikit-learn
• Machine learning with scikit-learn
• Step 1) Import the data
• Step 2) Create the train/test set
• Step 3) Build the pipeline
• Step 4) Using our pipeline in a grid search

11 : Linear Regression Tensorflow

• Linear regression
• How to train a linear regression model
• How to train a Linear Regression with TensorFlow
• Numpy Solution
• Tensorflow solution

12 : Linear Regression Case Study

• Summary statistics
• Facets Overview
• Facets Deep Dive
• Install Facet
• Overview
• Graph
• Facets Deep Dive

13 : Linear Classifier in TensorFlow

• What is Linear Classifier?
• How Binary classifier works?
• How to Measure the performance of Linear Classifier?
• Linear Classifier with TensorFlow

14 : Kernel Methods

• Why do you need Kernel Methods?
• What is a Kernel in machine learning?
• Type of Kernel Methods
• Train Gaussian Kernel classifier with TensorFlow

15 : TensorFlow ANN (Artificial Neural Network)

• What is Artificial Neural Network?
• Neural Network Architecture
• Limitations of Neural Network
• Example Neural Network in TensorFlow
• Train a neural network with TensorFlow

16 : ConvNet(Convolutional Neural Network): TensorFlow Image Classification

• What is Convolutional Neural Network?
• Architecture of a Convolutional Neural Network
• Components of Convnets
• Train CNN with TensorFlow

17 : Autoencoder with TensorFlow

• What is an Autoencoder?
• How does Autoencoder work?
• Stacked Autoencoder Example
• Build an Autoencoder with TensorFlow

18 : RNN(Recurrent Neural Network) TensorFlow

• What do we need an RNN?
• What is RNN?
• Build an RNN to predict Time Series in TensorFlow

01 : Introduction to PyTorch, Tensors, andTensor operations

• Using Tensors

02 : Probability Distributions Using PyTorch

• Sampling Tensors
• Variable Tensors
• Basic Statistics
• Gradient Computation
• Tensor Operations
• Tensor Operations
• Distributions

03 : CNN and RNN Using PyTorch

• Setting Up a Loss Function
• Estimating the Derivative of the Loss Function
• Fine-Tuning a Model
• Selecting an Optimization Function
• Further Optimizing the Function
• Implementing a Convolutional Neural Network (CNN)
• Reloading a Model
• Implementing a Recurrent Neural Network (RNN)
• Implementing a RNN for Regression Problems
• Using PyTorch Built-in Functions
• Working with Autoencoders
• . Fine-Tuning Results Using Autoencoder
• Visualizing the Encoded Data in a 3D Plot
• Restricting Model Overfitting
• Visualizing the Model Overfit
• Initializing Weights in the Dropout Rate
• Adding Math Operations
• Embedding Layers in RNN

04 : Introduction to Neural Networks Using PyTorch

• Working with Activation Functions
• Visualizing the Shape of Activation Functions
• Basic Neural Network Model
• Tensor Differentiation

05 : Supervised Learning Using PyTorch

• Data Preparation for the Supervised Model
• Forward and Backward Propagation
• Optimization and Gradient Computation
• Viewing Predictions
• Supervised Model Logistic Regression

06 : Fine-Tuning Deep Learning Models Using PyTorch

• Building Sequential Neural Networks
• Deciding the Batch Size5
• Deciding the Learning Rate
• Performing Parallel Training

07 : Natural Language Processing Using PyTorch

• Word Embedding
• CBOW Model in PyTorch
• LSTM Model

01 : An Introduction to Deep Learning and Keras

• Introduction to DL
• Demystifying the Buzzwords
• What Are Some Classic Problems Solved by DL in Today’s Market?
• Decomposing a DL Model
• Exploring the Popular DL Frameworks
• Low-Level DL Frameworks
• High-Level DL Frameworks
• A Sneak Peek into the Keras Framework
• Getting the Data Ready
• Defining the Model Structure
• Training the Model and Making Predictions
• Summary

02 : Keras in Action

• Setting Up the Environment
• Selecting the Python Version
• Installing Python for Windows, Linux, or macOS
• Installing Keras and TensorFlow Back End
• Getting Started with DL in Keras
• Input Data
• Neuron
• Activation Function
• Sigmoid Activation Function Model
• Layers
• The Loss Function Optimizers
• Metrics
• Model Configuration
• Model Training
• Model Evaluation
• Putting All the Building Blocks Together
• Summary

03 : Deep Neural Networks for Supervised Learning

• Regression
• Getting Started
• Problem Statement
• Why Is Representing a Problem Statement with a Design Principle
• Important?
• Designing an SCQ
• Designing the Solution
• Exploring the Data Looking at the Data Dictionary
• Finding Data Types
• Working with Time
• Predicting Sales
• Exploring Numeric Columns
• Understanding the Categorical Features Data Engineering
• Defining Model Baseline Performance
• Designing the DNN
• Testing the Model Performance
• Improving the Model
• Increasing the Number of Neurons
• Plotting the Loss Metric Across Epochs
• Testing the Model Manually
• Summary

04 : Deep Neural Networks for Supervised Learning

• Classification
• Getting Started
• Problem Statement
• Designing the SCQ
• Designing the Solution
• Exploring the Data
• Data Engineering
• Defining Model Baseline Accuracy
• Designing the DNN for Classification
• Revisiting the Data
• Standardize, Normalize, or Scale the Data
• Transforming the Input Data
• DNNs for Classification with Improved Data
• Summary

05 : Tuning and Deploying Deep Neural Networks

• The Problem of Overfitting
• So, What Is Regularization?
• L1 Regularization
• L2 Regularization
• Dropout Regularization
• Hyperparameter Tuning
• Hyperparameters in DL
• Approaches for Hyperparameter Tuning
• Model Deployment
• Tailoring the Test Data
• Saving Models to Memory
• Retraining the Models with New Data
• Online Models
• Delivering Your Model As an API
• Putting All the Pieces of the Puzzle Together
• Summary

06 : The Path Ahead

• What’s Next for DL Expertise?
• CNN
• RNN
• CNN + RNN
• Why Do We Need GPU for DL?
• Other Hot Areas in DL (GAN)

01: Artificial Neural Network

• The Neuron
• The Activation Function
• How do Neural Networks work?
• How do Neural Networks learn?
• Gradient Descent
• Stochastic Gradient Descent
• Backpropagation

02: Convolutional Neural Network

• What are Convolutional Neural Networks?
• The Convolution Operation
• Bis - The ReLU Layer
• Pooling
• Flattening
• Full Connection
• Softmax & Cross-Entropy

03: AutoEncoder

• What are AutoEncoders?
• A Note on Biases
• Training an AutoEncoder
• Overcomplete Hidden Layers
• Sparse AutoEncoders
• Denoising AutoEncoders
• Contractive AutoEncoders
• Stacked AutoEncoders
• Deep AutoEncoders

04: Variational AutoEncoder

• Introduction to the VAE
• Variational AutoEncoders
• Reparameterization Trick

05: Implementing the CNN-VAE

• Initializing all the parameters and variables of the CNN-VAE class
• Building the Encoder part of the VAE
• Building the "V" part of the VAE
• Building the Decoder part of the VAE
• Implementing the Training operations
• Full Code Section
• The Keras Implementation

06: Recurrent Neural Network

• What are Recurrent Neural Networks?
• The Vanishing Gradient Problem
• LSTMs
• LSTM Practical Intuition
• LSTM Variations

07: Mixture Density Network

• Mixture Density Networks
• VAE + MDN-RNN Visualization

08: Implementing the MDN-RNN

• Initializing all the parameters and variables of the MDN-RNN class
• Building the RNN - Gathering the parameters
• Building the RNN - Creating an LSTM cell with Dropout
• Building the RNN - Setting up the Input, Target, and Output of the RNN
• Building the RNN - Getting the Deterministic Output of the RNN
• Building the MDN - Getting the Input, Hidden Layer and Output of the MDN
• Building the MDN - Getting the MDN parameters
• Implementing the Training operations (Part 1)
• Implementing the Training operations (Part 2)
• Full Code Section
• The Keras Implementation

09: Reinforcement Learning

• What is Reinforcement Learning?
• A Pseudo Implementation of Reinforcement Learning for the Full World Model
• Full Code Section

10: Deep NeuroEvolution

• Deep NeuroEvolution
• Evolution Strategies
• Genetic Algorithms
• Covariance-Matrix Adaptation Evolution Strategy (CMA-ES)
• Parameter-Exploring Policy Gradients (PEPG)
• OpenAI Evolution Strategy

01 : Extracting the Data

• Collecting Data
• Collecting Data from PDFs
• Collecting Data from Word Files. 1-4. Collecting Data from JSON
• Collecting Data from HTML
• Parsing Text Using Regular Expressions
• Handling Strings
• Scraping Text from the Web

02 : Exploring and Processing Text Data

• Converting Text Data to Lowercase
• Removing Punctuation
• Removing Stop Words
• Standardizing Text
• Correcting Spelling
• Tokenizing Text
• Stemming
• Lemmatizing
• Exploring Text Data
• Building a Text Preprocessing Pipeline

03 : Converting Text to Features

• Converting Text to Features Using One Hot Encoding
• Converting Text to Features Using Count Vectorizing
• Generating N-grams
• Generating Co-occurrence Matrix
• Hash Vectorizing
• Converting Text to Features Using TF-IDF
• Implementing Word Embeddings
• Implementing fastText

04 : Advanced Natural Language Processing

• Extracting Noun Phrases
• Finding Similarity Between Texts
• Tagging Part of Speech
• Extract Entities from Text
• Extracting Topics from Text
• Classifying Text
• Carrying Out Sentiment Analysis
• Disambiguating Text
• Converting Speech to Text
• Converting Text to Speech
• Translating Speech

05 : Implementing Industry Applications

• Implementing Multiclass Classification
• Implementing Sentiment Analysis
• Applying Text Similarity Functions
• Summarizing Text Data
• Clustering Documents
• NLP in a Search Engine

06 : Deep Learning for NLP

• Retrieving Information
• Classifying Text with Deep Learning
• Next Word Prediction