Deep Learning: Getting Started

Deep Learning: Getting Started

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 1h 08m | 607 MB

Deep learning as a technology has grown leaps and bounds in the last few years. More and more AI solutions use deep learning as their foundational technology. Studying this technology, however, has several challenges. Most learning resources are math-heavy and are difficult to navigate without good math skills. IT professionals need a simplified resource to learn the concepts and build models quickly. This course aims to provide a simplified path to studying the basics of deep learning and becoming productive quickly. Instructor Kumaran Ponnambalam starts off with an intro to deep learning, including artificial neural networks and architectures. He navigates through various building blocks of neural networks with simple and easy to understand explanations. Kumaran also builds code in Keras to implement these building blocks. He then pulls it all together with an end-to-end exercise. Finally, test what you learned with a deep learning problem and compare your solution with Kumaran’s.

Table of Contents

1 Getting started with deep learning
2 Prerequisites for the course
3 Setting up the environment

Introduction to Deep Learning
4 What is deep learning
5 Linear regression
6 An analogy for deep learning
7 The perceptron
8 Artificial neural networks
9 Training an ANN

Neural Network Architecture
10 The input layer
11 Hidden layers
12 Weights and biases
13 Activation functions
14 The output layer

Training a Neural Network
15 Setup and initialization
16 Forward propagation
17 Measuring accuracy and error
18 Back propagation
19 Gradient descent
20 Batches and epochs
21 Validation and testing
22 An ANN model

Deep Learning Example 1
23 The Iris classification problem
24 Input preprocessing
25 Creating a deep learning model
26 Training and evaluation
27 Saving and loading models
28 Predictions with deep learning models

Deep Learning Example 2
29 Spam classification problem
30 Creating text representations
31 Building a spam model
32 Predictions for text

Deep Learning Exercise
33 Exercise problem statement
34 Preprocessing RCA data
35 Building the RCA model
36 Predicting root causes with deep learning

37 Extending your deep learning education