Deep Learning for Python Developers
0.0 (0 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
4 students enrolled

Deep Learning for Python Developers

Gain tireless accuracy and cost-efficiency with Deep Learning in Python
0.0 (0 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
4 students enrolled
Created by Packt Publishing
Last updated 2/2019
English
English [Auto]
Current price: $80.99 Original price: $124.99 Discount: 35% off
14 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 2 hours on-demand video
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Write software that reads handwriting, classifies images by what's in them, and decodes messages in sign language—even if you've never done machine learning before.
  • Build Deep Learning models that work at a much faster rate, never sleep, and get your tasks done quickly and efficiently
  • Develop an appreciation of Deep Learning models that are used in large scale, distributed settings in cloud computing
  • Apply your sequence models to natural language problems such as including text synthesis and audio applications, speech recognition, and music synthesis.
  • Build Convolutional Neural Networks, including recent variations such as residual networks
  • Understand the strengths and weaknesses of various frameworks and when it is best to apply them
  • Use intelligent automation to avoid errors and save the time normally spent fixing them.
Course content
Expand all 23 lectures 02:11:31
+ Getting Started with Deep Learning
6 lectures 30:19

This video will give you an overview about the course. 

Preview 03:20

The aim of this video is to learn the basics of machine learning and deep learning.

  • Understand machine learning versus deep learning

  • Fundamentals of neural networks

 

Fundamentals of Neural Networks
06:17

Learn what training a network actually means.

  • Understand loss functions

  • Understand optimizers

 

Training Deep Neural Networks
04:36

The aim of this video is to learn how machine learning algorithms work under the hood.

  • Understand gradients

  • Understand learning rates

  • Watch machine learning in action

 

Using Forward Propagation, Backprop, and SGD
04:43

The aim of this video is to learn how to implement the classic logistic regression algorithm with deep learning libraries.

  • Understand logistic regression

  • Loading and preparing data

  • Train a Keras logistic regression model

 

Logistic Regression with a Neural Network Mindset
04:15

The aim of this video is to learn how to work with the MNIST digits and recognize handwritten characters.

  • Acquire the MNIST data

  • Build a convolutional neural network

  • Understand softmax and the relationship with logistic regression

 

Convolutional Neural Network Handwriting Recognition
07:08
+ Deep Models with MxNet and TensorFlow
6 lectures 38:44

The aim of this video is to learn the basics of MxNet.

  • Understand fundamental MxNet data types

  • Understand the relationship of Gluon with MxNet

  • Implement logistic regression in Gluon

 

Preview 06:20

The aim of this video is to learn how to create a multilayer perceptron with MxNet.

  • Acquire MNIST digits

  • Build a multilayer perceptron with MxNet

  • Build a multilayer perceptron with Gluon

 

Defining and Training Neural Networks in MxNet/Gluon
07:22

The aim of this video is to learn the basics of TensorFlow and Keras.

  • Understand tensors and variables

  • Use TensorFlow neural network layers

  • Train a TensorFlow logistic regression model

 

Working with TensorFlow and Keras
05:21

Learn how to create a multilayer perceptron with Keras and TensorFlow.

  • Implement multilayer perceptron with TensorFlow

  • Implement multilayer perceptron with Keras

  • Compare the two implementations

 

Defining and Training Neural Networks in Keras/TensorFlow
04:38

The aim of this video is to understand the pros and cons of Keras and Gluon.

  • Explore more about Keras

  • Explore more about Gluon

  • Compare the frameworks' pros and cons

 

Comparing the Two Frameworks
03:03

In this video, we’ll build a model to classify CIFAR images.

  • Acquire the CIFAR images

  • Classify CIFAR with Alexnet

  • Classify CIFAR with VGG16

 

Mini Project - CIFAR Classification
12:00
+ Improving Deep Neural Networks
4 lectures 18:19

Learn why weight initialization is important for deep networks.

  • Understand weight initialization

  • Compare One and Zero initialization

  • Use Random initialization

 

Preview 03:35

The aim of this video is to learn how to combat overfitting.

  • Understand overfitting

  • Use regularization to combat overfitting

  • Use dropout to combat overfitting

 

Regularization and Dropout
03:25

In this video, we learn that normalizing improves learning.

  • Understand normalization

  • Train without normalized data

  • Train with normalized data

 

Normalizing and Vanishing/Exploding Gradients
03:29

Let’s create a project to recognize street sign images with machine learning.

  • Acquire and prepare the sign data

  • Build an initial network

  • Improve your network, the dropout, and batch normalization

 

Mini Project – SIGNS Dataset
07:50
+ Optimization Algorithms
3 lectures 19:36

Learn about visualizing machine learning in action.

  • Visualize a target function

  • Visualize learning

  • Visualize different learning rates

 

Understanding Stochastic Gradient Descent
06:27

The aim of this video is to understand the variable learning rate effect on machine learning.

  • Visualize a target function

  • Visualize RMSProp loss

  • Visualize Adam loss

 

Adaptive Learning Algorithms - RMSProp and Adam
04:05

Let’s create a network that can model a language and generate text.

  • Understand language modeling

  • Build a language model

  • Generate text with a language model

 

Mini Project - Language Modeling
09:04
+ Hyperparameter Tuning
4 lectures 24:33

What is a hyperparameter?

  • Define hyperparameters

  • Explore the role of hyperparameter turning

  • Understand the two approaches to hyperparameter tuning

 

Hyperparameters
04:23

The aim of this video is to understand the grid search approach to hyperparameter tuning.

  • Set up hyperparameter options

  • Set up a tunable model

  • Tune parameters

 

Tuning Hyperparameters - Grid Search
04:36

The aim of this video is to understand the random search approach to hyperparameter tuning.

  • Set up hyperparameter options

  • Set up a tunable model

  • Tune parameters

 

Tuning Hyperparameters - Random Search
04:50

Let’s create a machine learning model that can generate music.

  • Learn about MIDI files and music data

  • Build a sequence model to learn a MIDI representation

  • Generate new songs from a random seed

 

Mini Project - Music Synthesis
10:44
Requirements
  • Should have prior knowledge of Python.
Description

Deep learning is a new  superpower which will let you build AI systems that just weren't  possible a few years ago. It's time to utilize intelligent automation to  help your business grow, keep organized, and stay on top of the  competition.

This course is for Python developers who haven't worked with machine  learning or data science, and want to build intelligent systems right  away—without taking a math degree! You will learn about recurrent neural  networks, Backprop, SGD, and more. You will work on code examples that  are used in a developer's life on a daily basis; you'll not only master  the theory, you'll also see how to applied it in the industry as a  whole. You will practice all these ideas in MxNet, TensorFlow, Keras,  and Gluon. Last but not the least, build Convolutional Neural Networks  and apply them to image data.

Deep Learning is currently enabling numerous exciting applications in  speech recognition, music synthesis, machine translation, natural  language understanding, and many others. AI is transforming multiple  industries. After finishing this course, you will likely find creative  ways to apply it to your work. We will help you master Deep Learning,  understand how to apply it, and build a career in AI.

About the Author

Will Ballard is the Chief  Technology Officer at GLG, responsible for engineering and IT. He was  also responsible for the design and operation of large data centers that  helped run site services for customers including Gannett, Hearst  Magazines, NFL, NPR, The Washington Post, and Whole Foods. He has also  held leadership roles in software development at NetSolve (now Cisco),  NetSpend, and Works (now Bank of America). 

Who this course is for:
  • If you're a Python developer writing any kind of Python app/script, this course will get you working with Deep Learning in Python in no time.