English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 3h 26m | 578 MB
Learn to apply machine learning to your problems. Follow a complete pipeline including pre-processing and training
This course is for you if you are new to Machine Learning but want to learn it without all the math. This course is also for you if you have tried to use a machine learning course but could never figure out how to use it to solve your own problems.
In this course, we will start from scratch. So we will immediately start coding even before installation! You will see a brief bit of absolutely essential theory and then we will get into environment setup and explain almost all concepts through code. You will be using Keras, one of the easiest and most powerful machine learning tools out there.
You will start with a basic model of how machines learn and then move on to higher models, such as:
- Convolutional Neural Networks
- Residual connections
- Google’s Inception Module
All this with only a few lines of code. All the examples used in the course come with starter code which will get you started and without the hard work.
This course is based on a case study-based approach and explains why we need machine learning and how everything fits together.
What You Will Learn
- Basics of machine learning with minimal math
- A specialized but optional math-heavy discussion that explains all the inner working of machine learning and deep learning
- Applying machine learning principles to solve a real-world case study that includes pre-processing and getting your data into the proper shape. (This case study comes from real research work I have carried out recently.)
- Understand the often problematic shape issue that makes machine learning difficult to apply in real life
- Learn the details of ConvNets and graph-based machine learning models such as Residual Connections and Google’s Inception Module
- Use Keras’ functional API to create powerful models that will help you move way beyond the contents covered in this course
- Learn how to use Google’s GPUs to speed up your experiments for free
- Tips on avoiding mistakes made by newcomers to the field and best practices to get you to your goal with minimal effort
Table of Contents
01 Welcome and Introduction
02 About the Instructor
03 Dive into Machine Learning
04 Making Predictions
05 Machine Learning Pipeline
06 Regression
07 Binary and Multi-class Classification
08 Recap and a Link to More Theory
09 Environment setup for Windows (and some issues with it)
10 Environment setup for Mac and Linux
11 Data Preparation
12 Training and Testing
13 Problem Description and Data View
14 Pre-processing the Data
15 Loading Data and Getting the Shapes Right
16 Train, Test Split
17 Shapes in Depth (or how not to have headaches for days)
18 Sequential Model
19 Functional API
20 Basics and Rationale
21 CNN in Keras (or why Keras is better than your ML tool)
22 Pooling (and why it’s not that important)
23 Dropout (and why you should always consider it)
24 Functional API for CNN
25 Inception Module
26 Residual Connections
27 Saving and Loading Model Weights
28 Parting Words
Resolve the captcha to access the links!