• Post category:StudyBullet-8
  • Reading time:12 mins read


Uncover the Concepts and Techniques to Build and Train your own Artificial Intelligence Models

What you will learn

The basics of supervised learning: What are parameters, What is a bias node, Why do we use a learning rate

Techniques for dealing with data: How to Split Datasets, One-hot Encoding, Handling Missing Values

Vectors, matrices and creating faster code using Vectorization

Mathematical concepts such as Optimization, Derivatives and Gradient Descent

Gain a deep understanding behind the fundamentals of Feedforward, Convolutional and Recurrent Neural Networks

Build Feedforward, Convolutional and Recurrent Neural Networks using only the fundamentals

How to use Tensorflow 2.0 and Keras to build models, create TFRecords and save and load models

Practical project: Style Transfer – Use AI to draw an image in the style of your favorite artist

Practical project: Object Detection – Use AI to Detect the bounding box locations of objects inside of images

Practical project: Transfer Learning – Learn to leverage large pretrained AI models to work on new datasets

Practical project: One-Shot Learning – Learn to build AI models to perform tasks such as Face recognition

Practical project: Text Generation – Build an AI model to generate text similar to Romeo and Juliet

Practical project: Sentiment Classification – Build an AI model to determine whether text is overall negative or positive

Practical project: Attention Model – Build an attention model to build an interpretable AI model

Description

Gain a deep understanding of Supervised Learning techniques by studying the fundamentals and implementing them in NumPy.

Gain hands-on experience using popular Deep Learning frameworks such as Tensorflow 2 and Keras.

Section 1 – The Basics:

– Learn what Supervised Learning is, in the context of AI

– Learn the difference between Parametric and non-Parametric models

– Learn the fundamentals: Weights and biases, threshold functions and learning rates

– An introduction to the Vectorization technique to help speed up our self implemented code

– Learn to process real data: Feature Scaling, Splitting Data, One-hot Encoding and Handling missing data

– Classification vs Regression

Section 2 – Feedforward Networks:

– Learn about the Gradient Descent optimization algorithm.

– Implement the Logistic Regression model using NumPy

– Implement a Feedforward Network using NumPy

– Learn the difference between Multi-task and Multi-class Classification

– Understand the Vanishing Gradient Problem

– Overfitting

– Batching and various Optimizers (Momentum, RMSprop, Adam)

Section 3 – Convolutional Neural Networks:


Get Instant Notification of New Courses on our Telegram channel.


– Fundamentals such as filters, padding, strides and reshaping

– Implement a Convolutional Neural Network using NumPy

– Introduction to Tensorfow 2 and Keras

– Data Augmentation to reduce overfitting

– Understand and implement Transfer Learning to require less data

– Analyse Object Classification models using Occlusion Sensitivity

– Generate Art using Style Transfer

– One-Shot Learning for Face Verification and Face Recognition

– Perform Object Detection for Blood Stream images

Section 4 – Sequential Data

– Understand Sequential Data and when data should be modeled as Sequential Data

– Implement a Recurrent Neural Network using NumPy

– Implement LSTM and GRUs in Tensorflow 2/Keras

– Sentiment Classification from the basics to the more advanced techniques

– Understand Word Embeddings

– Generate text similar to Romeo and Juliet

– Implement an Attention Model using Tensorflow 2/Keras

English
language

Content

Introduction

Introduction
Syllabus
Setup Coding Environment Resources
Setup Coding Environment

The Basics

Artificial Intelligence Machine Learning Supervised Learning
Parameters and threshold function
Simple parametric model lab
Model Intuition and Lab
Learning rate and code clean up
A gentle introduction to vectors
Vectorization Lab
What is a Bias Node
Bias Node and Dynamic Decision Boundary Lab
The Perceptron Algorithm and Lab
Non-Binary Inputs and Feature Scaling
Working with Real Data
Working with Real Data Lab Part 1
Working with Real Data Lab Part 2
Saving and Loading Weights
Training Improvements
Classification vs Regression
019 – Limitations of Perceptrons

Feedforward Neural Networks

Introduction to Neural Networks
Logistic Regression Overview
A Gentle Introduction to Derivatives
Gradient Descent
Logistic Regression Equations
Logistic Regression Lab
Introduction to Matrices
Further Vectorization for Logistic Regression Lab
Notation for Neural Networks
Forward Propagation
Forward Propagation Lab
Backpropagation
Back Propagation Equation Derivations
Backpropagation Lab
Understanding Hidden Layers
Weight Intialization
Multi-Task and Multi-Class Classification
Derivatives of Softmax and Categorical Cross Entropy
Multi-Class Classification Lab
The Vanishing Gradient Problem and ReLu Activation Function
Relu Lab
Confusion Matrix Analysis
Overfitting
Batching Theory
Batching Lab
Code Cleanup
Optimizers – Momentum
Optimizers – Momentum Lab
Optimizers – RMS prop
RMSprop Lab
Optimizers – Adam
Optimizers – Adam Lab

Convolutional Neural Networks

CNN Section Overview
Image Data
Filters
Padding
Strides
Reshaping
Introducton to Convolutional Neural Networks
Convolutional Neural Networks Forward Propagation
CNN Forward Propagation Lab Part 1 – Parameter Initialization
CNN Forward Propagation Lab Part 2 – Forward Propagation Method
CNN Forward Propagation Lab Part 3 – Extract Patches and Test
Convolutional Neural Networks Backpropagation
Convolutional Neural Networks Backpropagation Lab
Pooling Layers
Pooling Lab Part 1 Forward Propagation (optional)
Pooling Lab Part 2 – Backpropagation (optional)
Introduction to Tensorflow Keras Part 1
Introduction to Tensorflow Keras Part 2
Creating a Custom Image Dataset – Part 1 Data Preparation
Creating a Custom Image Dataset – Part 2 Creating a Tensorflow Record
Using Tensorflow Records for Training
A Brief History of CNNs for Image Classifications
AlexNet Implementation Part 1 Data Preparation
AlexNet Implementation part 2 Model Definition
Transfer Learning
Occlusion Sensitivity
Style Transfer
Style Transfer Lab Part 1 – Setup
Style Transfer Lab Part 2 – Gram Matrix and Losses
Style Transfer Lab Part 3 – Training and Results
One Shot Learning Overview
Face Verification and Recognition Lab
Object Detection Architecture and Label Format
Object Detection Loss Function.mp4
Object Detection Lab Part 1 – Setup
Object Detection Lab Part 2 – Label Creation Loss Function and Training
Object Detection Making Predictions and Evaluating
Object Detection Lab Part 3 – Extracting Predictions
Object Detection Lab Part 4 – Non-max Suppression
Object Detection Lab Part 5 – F1 Score
CNN Section Summary

Sequential Data

Sequential Data Overview
Recurrent Neural Networks
Forward Propagation for RNNs
Data Prep and Forward Propagation Lab
Backpropagation for RNNs
Backpropagation and vanishing Gradient Lab
LSTM Theory
RNNs, LSTMS and GRUs in Tensorflow Lab
Character Based Text Generation
Word Embeddings
Exploring GloVe Word Embeddings Lab
Advanced Sentiment Classification with GloVe
Advanced Sentiment Classification with BERT
Attention Models Theory
Attention Models Lab Part 1 Model Definition and Training
Attention Models Lab Part 2 Visualizing Attention
Sequential Data Summary

Conclusion

Thank you, and where to from here?