Keras: Deep Learning in Python

Keras: Deep Learning in Python, available at $44.99, has an average rating of 3.65, with 39 lectures, 2 quizzes, based on 157 reviews, and has 1067 subscribers.

You will learn about Use Keras for classification and regression in typical data science problems Use Keras for image classification Define Convolutional neural networks Train LSTM models for sequences Process the data in order to achieve to the specific shape that Keras expects for each problem Code neural networks directly in Theano using tensor multiplications Understand what are the different layers that we have in Keras Design neural networks that mitigate the effect of overfitting using specific layers Understand how backpropagation and stochastic gradient descent work This course is ideal for individuals who are Students beginning with machine learning but who already are comfortable with Python or Business analytics professionals aiming to expand their toolkit of analytical techniques It is particularly useful for Students beginning with machine learning but who already are comfortable with Python or Business analytics professionals aiming to expand their toolkit of analytical techniques.

Enroll now: Keras: Deep Learning in Python

Summary

Title: Keras: Deep Learning in Python

Price: $44.99

Average Rating: 3.65

Number of Lectures: 39

Number of Quizzes: 2

Number of Published Lectures: 39

Number of Published Quizzes: 2

Number of Curriculum Items: 41

Number of Published Curriculum Objects: 41

Original Price: £19.99

Quality Status: approved

Status: Live

What You Will Learn

Use Keras for classification and regression in typical data science problems
Use Keras for image classification
Define Convolutional neural networks
Train LSTM models for sequences
Process the data in order to achieve to the specific shape that Keras expects for each problem
Code neural networks directly in Theano using tensor multiplications
Understand what are the different layers that we have in Keras
Design neural networks that mitigate the effect of overfitting using specific layers
Understand how backpropagation and stochastic gradient descent work

Who Should Attend

Students beginning with machine learning but who already are comfortable with Python
Business analytics professionals aiming to expand their toolkit of analytical techniques

Target Audiences

Students beginning with machine learning but who already are comfortable with Python
Business analytics professionals aiming to expand their toolkit of analytical techniques

Do you want to build complex deep learning models in Keras? Do you want to use neural networks for classifying images, predicting prices, and classifying samples in several categories?

Keras is the most powerful library for building neural networks models in Python. In this course we review the central techniques in Keras, with many real life examples. We focus on the practical computational implementations, and we avoid using any math.

The student is required to be familiar with Python, and machine learning; Some general knowledge on statistics and probability is recommended, but not strictly necessary.

Among the many examples presented here, we use neural networks to tag images belonging to the River Thames, or the street; to classify edible and poisonous mushrooms, to predict the sales of several video games for multiple regions, to identify bolts and nuts in images, etc.

We use most of our examples on Windows, but we show how to set up an AWS machine, and run our examples there. In terms of the course curriculum, we cover most of what Keras can actually do: such as the Sequential model, the model API, Convolutional neural nets, LSTM nets, etc. We also show how to actually bypass Keras, and build the models directly in Theano/Tensorflow syntax (although this is quite complex!)

After taking this course, you should feel comfortable building neural nets for time sequences, images classification, pure classification and/or regression. All the lectures here can be downloaded and come with the corresponding material.

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Lecture 2: Installing Keras

Lecture 3: Theano and Tensorflow

Lecture 4: Running high performance code in AWS

Chapter 2: Keras fundamentals

Lecture 1: Introduction to the Sequential Model

Lecture 2: Activation functions

Lecture 3: Layers

Lecture 4: Training

Lecture 5: Loss functions

Lecture 6: Overfitting: Gaussian Noise and Dropout layers

Lecture 7: Wine classification

Lecture 8: Mushroom classification

Lecture 9: House Prices in the US

Lecture 10: Stochastic gradient descent

Lecture 11: Backpropagation: How Neural Nets are trained

Lecture 12: Clipvalue and learning rate

Lecture 13: Optimizers

Lecture 14: Locally connected layers and 1D Convolutions

Lecture 15: Pulling weights from Layers

Lecture 16: Car Prices in Germany: Batch processing

Lecture 17: The model API: Merging layers and more complex models

Lecture 18: Videogames: Multi output predictions

Chapter 3: Scikit-learn and Keras

Lecture 1: Scikit-learn with Keras: Comparing deep learning models

Lecture 2: Determining best parameters in Neural Networks using GridSearchCV

Chapter 4: Classes for images

Lecture 1: A class that maps BW images to Python objects

Lecture 2: A class that maps RGB Images to Python objects

Chapter 5: Multilayer Perceptron

Lecture 1: Structure

Lecture 2: Coding a Multilayer Perceptron in pure Theano: Part1

Lecture 3: Coding a Multilayer Perceptron in pure Theano: Part2

Lecture 4: Multilayer Perceptron in Keras

Chapter 6: Convolutional Neural Nets

Lecture 1: Introduction

Lecture 2: Convolutions and Max-Pooling

Lecture 3: Predicting Hand Gestures

Lecture 4: Classifying bolts and nuts

Lecture 5: Classifying Pictures in park vs home

Chapter 7: Recurrent neural networks

Lecture 1: Recurrent Neural Networks

Lecture 2: The vanishing gradient

Lecture 3: LSTM: Predicting House Prices in London

Lecture 4: Predicting global temperatures

Instructors

Francisco Juretig
Mr

Rating Distribution

1 stars: 13 votes
2 stars: 15 votes
3 stars: 32 votes
4 stars: 48 votes
5 stars: 49 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!

Menu