مطالب پیشنهادی از سراسر وب

آموزش پروژه های یادگیری عمیق با PyTorch 

دسته بندی ها: آموزش پای تورچ (PyTorch) ، آموزش پایتون (Python) ، آموزش های Packtpub

PyTorch یک فریمورک یادگیری عمیق است که محرک محققان و دانشمندان داده است. PyTorch از Graphic Processing Units پشتیبانی و حداکثر انعطاف پذیری و سرعت را فراهم می کند. با PyTorch، شما می توانید به صورت پویا شبکه های عصبی را بسازید و به راحتی کارهای هوش مصنوعی پیشرفته انجام دهید. در این دوره با  مبانی PyTorch و نحوه استفاده از فرمان ها، شبکه های عصبی پیچشی، RNN و LSTM و غیره آشنا می شوید.

سرفصل:

  • معرفی دوره
  • استفاده از PyTorch
  • درک رگرسیون
  • رگرسیون خطی و منطقی
  • شبکه های عصبی پیچشی
  • ایجاد CNN
  • لایه خروجی
  • درک RNN و LSTM
  • استفاده از Autoencoders برای تشخیص تقلب
  • توسعه یک مدل
  • گرفتن خروجی
  • معرفی ماشین های Boltzmann
  • Recommender System
  • استفاده از Autoencoders
  • مقدمه ای بر Autoencoders
  • آماده شدن برای سیستم توصیه شده
  • و غیره
آیا این نوشته را دوست داشتید؟
Deep Learning Projects with PyTorch [Video] Publisher:Packtpub Author:Ashish Singh Bhatia Duration:3 hours

Step into the world of PyTorch to create deep learning models with the help of real-world examples
PyTorch is a Deep Learning framework that is a boon for researchers and data scientists. It supports Graphic Processing Units and is a platform that provides maximum flexibility and speed. With PyTorch, you can dynamically build neural networks and easily perform advanced Artificial Intelligence tasks.
The course starts with the fundamentals of PyTorch and how to use basic commands. Next, you’ll learn about Convolutional Neural Networks (CNN) through an example of image recognition, where you’ll look into images from a machine perspective.
The next project shows you how to predict character sequence using Recurrent Neural Networks (RNN) and Long Short Term Memory Network (LSTM). Then you’ll learn to work with autoencoders to detect credit card fraud. After that, it’s time to develop a system using Boltzmann Machines, where you’ll recommend whether to watch a movie or not.
We’ll continue with Boltzmann Machines, where you’ll learn to give movie ratings using AutoEncoders. In the end, you’ll get to develop and train a model to recognize a picture or an object from a given image using Deep Learning, where we’ll not only detect the shape, but also the color of the object.
By the end of the course, you’ll be able to start using PyTorch to build Deep Learning models by implementing practical projects in the real world. So, grab this course as it will take you through interesting real-world projects to train your first neural nets.
Style and Approach
This course takes a practical approach and is filled with real-world examples to help you create your own application using PyTorch.
Released: Wednesday, June 27, 2018
Getting Ready with PyTorch
The Course Overview
Using PyTorch
Understanding Regression
Linear Regression and Logistic Regression
Convolutional Neural Network
Understanding Convolutional Neural Network
Looking into Images from a Machine Perspective
Making CNN
Pooling Layers
Output Layer
Understanding RNN and LSTM
Understanding Recurrent Neural Network
Making RNN for Prediction
Why LSTM?
Moving to LSTM
Using Autoencoders for Fraud Detection
Getting Ready with Data
Developing a Model
Getting Output
Recommending a Movie with Boltzmann Machines
Introduction to Boltzmann Machines
Getting Ready for Recommender System
Making Boltzmann Machines
Getting Output
Movie Rating Using a Autoencoders
Introduction to Autoencoders
Getting Ready for Recommender System
Making Autoencoders
Getting Output
Making Model for Object Recognition
Getting Ready with Data
Developing a Model
Getting Output

پیشنهاد آموزش مرتبط در فرادرس

لینک های دانلود حجم فایل: 680.0MB Packtpub Deep Learning Projects with PyTorch [Video]_git.ir.rar