پیشنهاد فرادرس

آموزش ساخت مدل های یادگیری عمیق با Apache MXNet

دسته بندی ها: شبکه های عصبی مصنوعی ، آموزش های پلورال سایت (Pluralsight) ، هوش مصنوعی

Apache MXNet درواقع API های سطح پایین و سطح بالایی را ارائه می دهد که کلیدی برای ساخت شبکه های عصبی است. همچنین به شما اجازه می دهد که نمودارهای استاتیک و پویا را به شیوه ای نمادین با استفاده از Module API، Symbol API یا Gluon API بسازید. در این دوره با ایجاد شبکه های عصبی با NDArrays، Module API، Symbol API و Gluon API، درک معماری MXNet، نحوه کارکرد NDArrays ساختار داده، تفاوت بین برنامه نویسی نمادین و دستوری، استفاده از optimizers، توابع loss و data iterators در ایجاد و اجرای شبکه های عصبی، بررسی Gluon API، ایجاد شبکه عصبی پیچشی و غیره آشنا می شوید.

سرفصل:

  • معرفی دوره
  • معرفی Apache MXNet
  • پیش نیازهای دوره
  • نورون ها و شبکه های عصبی
  • نصب Apache MXNet
  • برنامه نویسی نمادین و دستوری
  • معرفی NDArrays
  • کار با NDArrays
  • ایجاد شبکه های عصبی با Module API
  • معرفی Symbol API
  • Data Iterators
  • معرفی Module API
  • برآوردگرها در Module API
  • ایجاد شبکه های عصبی با  Gluon API
  • معرفی  Gluon API
  • کار با Autograd
  • تکنیک های پیش پردازش تصویر
  • Gluon Model Zoo
  • و غیره
Building Deep Learning Models Using Apache MXNet Publisher:Pluralsight Author:Janani Ravi Duration:2h 3m Level:Beginner

Apache MXNet is the deep learning framework which has its origins at Amazon Web Services (AWS) and is a powerful alternative to TensorFlow. This course teaches you how to build dynamic and static computation graphs using the Gluon API.
Apache MXNet offers low-level and high-level APIs which is key to efficiently build neural networks. It also allows you to construct static and dynamic graphs in a symbolic manner using the Module API, the Symbol API, or the Gluon API. In this course, Building Deep Learning Models Using Apache MXNet, you'll learn the basic building blocks of building neural networks using NDArrays, the Module API, the Symbol API, as well as the cutting edge Gluon API. First, you'll gain an understanding of the basic architecture of MXNet and how the basic data structure NDArrays work. Next, you'll discover the difference between symbolic and imperative programming and when you would choose to use one over the other. Then, you'll discover the use of optimizers, loss functions, and data iterators in building and executing neural networks. Finally, you'll explore the Gluon API and build a convolutional neural network for image classification and hybridize it in order to execute a static computation graph. By the end of this course, you'll have the confidence to efficiently build and execute neural networks using all of the APIs that Apache MXNet has to offer.
Course Overview
Course Overview
1m
Introduction to Apache MXNet
Module Overview
1m
Prerequisites and Course Outline
2m
Neurons and Neural Networks
5m
Introducing Apache MXNet
4m
Demo: Installing Apache MXNet
2m
Symbolic and Imperative Programming
7m
Introducing NDArrays
2m
Demo: Working with NDArrays
4m
Demo: Advanced Operations on NDArrays
4m
Gradient Descent Optimization
3m
Forward and Backward Passes
3m
Building Neural Networks Using the Module API
Module Overview
0m
Introducing the Symbol API
3m
Demo: Computation Graphs Using the Symbol API
6m
Demo: Data Iterators
4m
Introducing the Module API
4m
Demo: Exploring the Breast Cancer Dataset and Setting up the NN
6m
Demo: Training and Prediction Using the Module API
4m
Demo: Estimators in the Module API
2m
Building Neural Networks Using the Gluon API
Module Overview
1m
Introducing the Gluon API
4m
Introducing the Autograd Package for Gradient Calculation
6m
Demo: Working with Autograd
2m
Convolution, Pooling, and CNN Architectures
4m
Image Pre-processing Techniques
1m
Demo: Loading, Exploring, and Transforming the CIFAR-10 Dataset
6m
Demo: Building and Training a CNN Using the Gluon API
5m
Demo: Hybridize the Neural Network for Symbolic Execution
3m
Transfer Learning
2m
The Gluon Model Zoo
1m
Demo: Image Classification Using a Pre-trained Model
5m
Summary and Further Study
1m

پیشنهاد فرادرس