About the course
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 had a machine learning course but could never figure out how to use it to solve your own problems.
Who Should Attend?
Anyone who:
- Wants to learn machine learning (this course is a soft introduction)
- Knows machine learning and wants to learn deep learning (this course focuses on deep learning)
Curriculum
Lesson 1: Introduction to Machine Learning
-
Lecture 1: About the InstructorFree
00:01:37
-
Lecture 2: MNIST Dataset Description and Data LoadingFree
00:13:10
-
Lecture 3: Making Predictions
00:07:01
Lesson 2: A Bit of Theory
-
Lecture 1: Machine Learning Pipeline
00:09:13
-
Lecture 2: Regression
00:13:01
-
Lecture 3: Binary and Multi-class Classification
00:14:29
-
Lecture 4: Recap and a Link to More TheoryFree
00:02:43
Lesson 3: Installation and Setup
-
00:06:55
-
Lecture 2: Environment setup for Mac and Linux
00:03:41
Lesson 4: Say Hi to Keras
-
Lecture 1: Data Preparation
00:10:10
-
Lecture 2: Training and Testing
00:10:32
Lesson 5: Real World Case Study: Predicting Protein Functions
-
Lecture 1: Problem Description and Data View
00:08:32
-
Lecture 2: Pre-processing the Data
00:15:51
-
Lecture 3: Loading Data and Getting the Shapes Right
00:07:45
-
Lecture 4: Train, Test Split
-
00:04:32
-
Lecture 6: Sequential Model
00:08:58
-
Lecture 7: Functional API
00:05:25
Lesson 6: Convolutional Neural Networks (CNN)
-
Lecture 1: Basics and Rationale
00:10:13
-
00:08:30
-
Lecture 3: Pooling (and why it's not that important)
00:04:25
-
00:03:51
Lesson 7: Graph-based Models
-
Lecture 1: Functional API for CNN
00:04:27
-
Lecture 2: Inception Module
00:09:36
-
Lecture 3: Residual Connections
00:05:08
Lesson 8: Parting Words
-
Lecture 1: Saving and loading model weights
00:06:30
-
Lecture 2: Parting words and future directions
00:03:55
Library
Storage
-
.zip complete-source-code
