14:43

Making Your Project Presentable: Last Touches for an Impressive Portfolio

05:01

Bonus lesson: Turning a Regression Problem into a Classification Problem

09:07

Is your model actually that good? Validating Machine Learning Models

07:56

Improve Machine Learning Model Performance with Tuning

14:08

Step-by-Step Preparing and Training a Machine Learning Model

17:16

Feature Engineering: Integrate a new data source into your dataset

06:59

Feature Engineering: Create new features using existing data

08:10

The Basics of Evaluating Machine Learning Projects

09:01

How to Train a Benchmark Model for your Machine Learning Project

06:25

Problem Definition and Data Preparation for a Real-Life Data Science Project

04:29

Extract Hour, Day, Month Info from Pandas DateTime

08:29

Fixing Incorrect Column Types in Pandas to Prepare Data for ML

02:13

Data Cleaning after Identifying Data Problems in Pandas

09:18

Data Exploration: Identifying Data Issues and Their Potential Causes

12:27

Using Data Visualization to Identify Data Problems

08:53

How Collecting Data Works on a Real-Life Data Science Project

11:27

Creating a GitHub Repository for a Data Science Project

10:34

Introduction to Jupyter Notebooks: explore the main functionalities

04:48

How to Set up a Data Science Development Environment

06:46

Hands-on Data Science course: Let's build a project together from scratch!

02:39

Key Concepts and Techniques for Natural Language Processing

01:46

How are training and tuning different?

02:24

Python vs. R comparison (by a die-hard Python fan)

01:54

Data Visualization Libraries For Python

02:20

Why do we split data into train test and validation sets?

02:47

How to fix missing values in your data

01:43

Quick explanation: One-hot encoding

02:43

How to Implement CNNs in Keras

14:32

CNN follow along calculations

12:19

Basics of Convolutional Neural Networks

15:57

Basics of Recurrent Neural Networks

10:18

LSTMs and GRUs

07:02

How to Implement RNNs in Keras

02:57

Training a Network for Better Performance

12:09

How to Tune a Neural Network

04:13

How to Understand What's Wrong with a Neural Network

07:32

Advanced Methods for Hyperparameter Tuning

06:46

Simple Methods for Hyperparameter Tuning

03:35

Tuning a Neural Network | Deciding on next steps to take

10:01

What is the Optimal Performance of a Neural Network?

04:23

How to Decide Whether Your Neural Network is Doing Well

07:13

How to Evaluate a Neural Network's Performance

06:28

Part 4: Tuning the Neural Network for Better Performance

07:24

Part 3: Training the Neural Network

07:27

Part 2: Best Settings to Initialize Your NN with

03:56

Part 1: Getting Ready to Build your First Advanced Neural Network

05:43

Part 5: Tips and Tricks on How to Initialize Your Neural Network

11:04

How to Make Neural Networks Train Faster on Keras

08:10

How to Use Learning Rate Scheduling for Neural Network Training

02:01

Pruning a neural Network for faster training times

13:48

How to select the correct optimizer for Neural Networks

14:08

How (and Why) to Use Mini-Batches in Neural Networks

03:29

Normalizing data for better Neural Network performance

02:05

How to Lower Neural Network Training Times

10:06

How to Solve Vanishing Gradients in Keras and Python

06:43

Gradient Clipping and How it Helps with Exploding Gradients in Neural Networks

13:23

How Does Batch Normalization Work

05:37

How to Choose an Activation Function for Neural Networks

03:53

How to Choose the Correct Initializer for your Neural Network

06:07

What is Vanishing/Exploding Gradients Problem in NNs