HOT
blank

Applied Deep Learning with Keras

Development

Rating4.4
Enroll Now

Applied Deep Learning with Keras, available at $19.99, has an average rating of 4.42, with 108 lectures, 9 quizzes, based on 6 reviews, and has 87 subscribers.

You will learn about Understand the difference between single-layer and multi-layer neural network models Use Keras to build simple logistic regression models, deep neural networks, recurrent neural networks, and convolutional neural networks Apply L1, L2, and dropout regularization to improve the accuracy of your model Implement cross-validate using Keras wrappers with scikit-learn Understand the limitations of model accuracy This course is ideal for individuals who are If you have basic knowledge of data science and machine learning and want to develop your skills and learn about artificial neural networks and deep learning, you will find this course useful. It is particularly useful for If you have basic knowledge of data science and machine learning and want to develop your skills and learn about artificial neural networks and deep learning, you will find this course useful.

Enroll now: Applied Deep Learning with Keras

Summary

Title: Applied Deep Learning with Keras

Price: $19.99

Average Rating: 4.42

Number of Lectures: 108

Number of Quizzes: 9

Number of Published Lectures: 108

Number of Published Quizzes: 9

Number of Curriculum Items: 117

Number of Published Curriculum Objects: 117

Original Price: $199.99

Quality Status: approved

Status: Live

What You Will Learn

  • Understand the difference between single-layer and multi-layer neural network models
  • Use Keras to build simple logistic regression models, deep neural networks, recurrent neural networks, and convolutional neural networks
  • Apply L1, L2, and dropout regularization to improve the accuracy of your model
  • Implement cross-validate using Keras wrappers with scikit-learn
  • Understand the limitations of model accuracy

Who Should Attend

  • If you have basic knowledge of data science and machine learning and want to develop your skills and learn about artificial neural networks and deep learning, you will find this course useful.

Target Audiences

  • If you have basic knowledge of data science and machine learning and want to develop your skills and learn about artificial neural networks and deep learning, you will find this course useful.

Though designing neural networks is a sought-after skill, it is not easy to master. With Keras, you can apply complex machine learning algorithms with minimum code.

Applied Deep Learning with Keras starts by taking you through the basics of machine learning and Python all the way to gaining an in-depth understanding of applying Keras to develop efficient deep learning solutions. To help you grasp the difference between machine and deep learning, the course guides you on how to build a logistic regression model, first with scikit-learn and then with Keras. You will delve into Keras and its many models by creating prediction models for various real-world scenarios, such as disease prediction and customer churning. You’ll gain knowledge on how to evaluate, optimize, and improve your models to achieve maximum information. Next, you’ll learn to evaluate your model by cross-validating it using Keras Wrapper and scikit-learn. Following this, you’ll proceed to understand how to apply L1, L2, and dropout regularization techniques to improve the accuracy of your model. To help maintain accuracy, you’ll get to grips with applying techniques including null accuracy, precision, and AUC-ROC score techniques for fine tuning your model.

By the end of this course, you will have the skills you need to use Keras when building high-level deep neural networks.

About the Author

Ritesh Bhagwathas a master’s degree in applied mathematics with a specialization in computer science. He has over 14 years of experience in data-driven technologies and has led and been a part of complex projects ranging from data warehousing and business intelligence to machine learning and artificial intelligence. He has worked with top-tier global consulting firms as well as large multinational financial institutions. Currently, he works as a data scientist. Besides work, he enjoys playing and watching cricket and loves to travel. He is also deeply interested in Bayesian statistics.

Mahla Abdolahnejadis a Ph.D. candidate in systems and computer engineering with Carleton University, Canada. She also holds a bachelor’s degree and a master’s degree in biomedical engineering, which first exposed her to the field of artificial intelligence and artificial neural networks, in particular. Her Ph.D. research is focused on deep unsupervised learning for computer vision applications. She is particularly interested in exploring the differences between a human’s way of learning from the visual world and a machine’s way of learning from the visual world, and how to push machine learning algorithms toward learning and thinking like humans.

Matthew Moocarme is a director and senior data scientist in Viacom’s Advertising Science team. As a data scientist at Viacom, he designs data-driven solutions to help Viacom gain insights, streamline workflows, and solve complex problems using data science and machine learning.

Matthew lives in New York City and outside of work enjoys combining deep learning with music theory. He is a classically-trained physicist, holding a Ph.D. in Physics from The Graduate Center of CUNY and is an active Artificial Intelligence developer, researcher, practitioner, and educator.

Course Curriculum

Chapter 1: Introduction to Machine Learning with Keras

Lecture 1: Course Overview

Lecture 2: Installation and Setup

Lecture 3: Lesson Overview

Lecture 4: Data Representation

Lecture 5: Loading a Dataset from the UCI Machine Learning Repository

Lecture 6: Data Pre-Processing

Lecture 7: Cleaning the Data

Lecture 8: Appropriate Representation of the Data

Lecture 9: Lifecycle of Model Creation

Lecture 10: Machine Learning Libraries and scikit-learn

Lecture 11: Keras

Lecture 12: Model Training

Lecture 13: Creating a Simple Model

Lecture 14: Model Tuning

Lecture 15: Regularization

Lecture 16: Lesson Summary

Lecture 17: Activity 1: Adding Regularization to the Model

Lecture 18: Solution 1: Adding Regularization to the Model

Chapter 2: Machine Learning versus Deep Learning

Lecture 1: Lesson Overview

Lecture 2: Introduction to ANNs

Lecture 3: Linear Transformations

Lecture 4: Matrix Transposition

Lecture 5: Introduction to Keras

Lecture 6: Lesson Summary

Lecture 7: Activity 2: Creating a Logistic Regression Model Using Keras

Lecture 8: Solution 2: Creating a Logistic Regression Model Using Keras

Chapter 3: Deep Learning with Keras

Lecture 1: Lesson Overview

Lecture 2: Building Your First Neural Network

Lecture 3: Gradient Descent for Learning the Parameters

Lecture 4: Model Evaluation

Lecture 5: Lesson Summary

Lecture 6: Activity 3: Building a Single-Layer Neural Network for Performing Binary Classif

Lecture 7: Solution 3: Building a Single-Layer Neural Network

Lecture 8: Activity 4: Diabetes Diagnosis with Neural Networks

Lecture 9: Solution 4: Diabetes Diagnosis with Neural Networks

Chapter 4: Evaluate Your Model with Cross-Validation using Keras Wrappers

Lecture 1: Lesson Overview

Lecture 2: Cross-Validation

Lecture 3: Cross-Validation for Deep Learning Models

Lecture 4: Evaluate Deep Neural Networks with Cross-Validation

Lecture 5: Model Selection with Cross-validation

Lecture 6: Write User-Defined Functions to Implement Deep Learning Models with Cross-Valida

Lecture 7: Lesson Summary

Lecture 8: Activity 5: Model Evaluation Using Cross-Validation

Lecture 9: Solution 5: Model Evaluation Using Cross-Validation

Lecture 10: Solution 5: Model Evaluation Using Cross-Validation

Lecture 11: Solution 6: Model Selection Using Cross-Validation

Lecture 12: Activity 7: Model Selection for Diabetes Diagnosis

Lecture 13: Solution 7: Model Selection for Diabetes Diagnosis

Chapter 5: Improving Model Accuracy

Lecture 1: Lesson Overview

Lecture 2: Regularization

Lecture 3: L1 and L2 Regularization

Lecture 4: Dropout Regularization

Lecture 5: Other Regularization Methods

Lecture 6: Data Augmentation

Lecture 7: Hyperparameter Tuning with scikit-learn

Lecture 8: Lesson Summary

Lecture 9: Activity 8: Weight Regularization on a Diabetes Diagnosis Classifier

Lecture 10: Solution 8: Weight Regularization on a Diabetes Diagnosis Classifier

Lecture 11: Activity 9: Dropout Regularization on Boston Housing Dataset

Lecture 12: Solution 9: Dropout Regularization on Boston House Prices Dataset

Lecture 13: Activity 10: Hyperparameter Tuning on the Diabetes Diagnosis Classifier

Lecture 14: Solution 10: Hyperparameter Tuning on the Diabetes Diagnosis Classifier

Chapter 6: Model Evaluation

Lecture 1: Lesson Overview

Lecture 2: Accuracy

Lecture 3: Imbalanced Datasets

Lecture 4: Confusion Matrix

Lecture 5: Computing Accuracy and Null Accuracy with Healthcare Data

Lecture 6: Calculate the ROC and AUC Curves

Lecture 7: Lesson Summary

Lecture 8: Activity 11: Computing the Accuracy and Null Accuracy of a Neural Network

Lecture 9: Solution 11: Computing the Accuracy and Null Accuracy of a Neural Network

Lecture 10: Activity 12: Derive and Compute Metrics Based on a Confusion Matrix

Lecture 11: Solution 12: Derive and Compute Metrics Based on the Confusion Matrix Solution

Chapter 7: Summarize your learning from this lesson.

Lecture 1: Lesson Overview

Lecture 2: Computer Vision

Lecture 3: Architecture of a CNN

Lecture 4: Image Augmentation

Lecture 5: Amending Our Model by Reverting to the Sigmoid Activation Function

Lecture 6: Changing the Optimizer from Adam to SGD

Lecture 7: Classifying a New Image

Lecture 8: Lesson Summary

Lecture 9: Activity 13: Amending our Model with Multiple Layers and the Use of SoftMax

Lecture 10: Solution 13: Amending our Model with Multiple Layers and Use of SoftMax

Lecture 11: Activity 14: Classify a New Image

Lecture 12: Solution 14: Classify a New Image

Chapter 8: Transfer Learning and Pre-trained Models

Instructors

Rating Distribution

  • 1 stars: 0 votes
  • 2 stars: 0 votes
  • 3 stars: 1 votes
  • 4 stars: 2 votes
  • 5 stars: 3 votes

Frequently Asked Questions


How long do I have access to the course materials?


You can view and review the lecture materials indefinitely, like an on-demand channel.


Can I take my courses with me wherever I go?


Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

You may also like

Top 10 Ethical AI Courses to Learn in November 2024

Top 10 Game Development Courses to Learn in November 2024

Top 10 Software Testing Courses to Learn in November 2024