**PyTorch Bootcamp for Artificial Neural Networks and Deep Learning Applications**

English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 3h 15m | 5.30 GB

Hands-on PyTorch boot camp for Artificial Intelligence applications with artificial neural networks and deep learning

Master the latest and hottest deep learning frameworks (PyTorch) for Python data science

This course is your complete guide to practical machine learning and deep learning using the PyTorch framework in Python and covers the important aspects of PyTorch. If you take this course, you’ll have no need to take other courses or buy books on PyTorch.

In this age of big data, companies across the Globe use Python to sift through the avalanche of information at their disposal; the advent of frameworks such as PyTorch is revolutionizing deep learning.

By gaining proficiency in PyTorch, you can give your company a competitive edge and take your career to the next level.

After taking this course, you’ll be able to use packages such as Numpy, Pandas, and PIL to work with real data in Python and you’ll be fluent in PyTorch. We even introduce you to deep learning models such as Convolution Neural Networks (CNNs)!

The underlying motivation for the course is to ensure you can apply Python-based data science on real data today, start analyzing data for your own projects whatever your skill level, and impress potential employers with actual examples of your data science abilities.

Learn

- Deep Learning Basics – Getting started with Anaconda, an important Python data science environment
- Neural Network Python Applications – Configuring the Anaconda environment to get started with PyTorch
- Introduction to Deep Learning Neural Networks – Theoretical underpinnings of important concepts (such as deep learning) without the jargon
- AI Neural Networks – Implementing Artificial Neural Networks (ANNs) with PyTorch
- Neural Network Model – Implementing deep learning (DL) models with PyTorch
- Deep Learning AI – Implement common machine learning algorithms for image classification
- Deep Learning Neural Networks – Implement PyTorch-based deep learning algorithms on image data

**Introduction to the Course – Welcome to the PyTorch Primer**

1 Welcome to PyTorch

2 Get Started with the Python Data Science Environment – Anaconda

3 Anaconda for Mac Users

4 Why PyTorch

5 Install PyTorch

6 Further Installation Instructions for Mac

7 Working with CoLabs

**Introduction to Python Data Science Packages (Other Than PyTorch)**

8 Python Packages for Data Science

9 Introduction to Numpy

10 Create Numpy Arrays

11 Numpy Operations

12 Numpy for Basic Vector Arithmetric

13 Numpy for Basic Matrix Arithmetic

14 PyTorch Basics – What Is a Tensor

15 Explore PyTorch Tensors and Numpy Arrays

16 Some Basic PyTorch Tensor Operations

**Other Python Data Science Packages for Dealing with Data**

17 Read in CSV data

18 Read in Excel data

19 Basic Data Exploration with Pandas

**Basic Statistical Analysis with PyTorch**

20 Ordinary Least Squares (OLS) Regression- Theory

21 OLS Linear Regression-Without PyTorch

22 OLS Linear Regression from First Principles-Theory

23 OLS Linear Regression from First Principles-With PyTorch

24 More OLS With PyTorch

25 Generalised Linear Models (GLMs)-Theory

26 Logistic Regression-Without PyTorch

27 Logistic Regression-With PyTorch

**Introduction to Artificial Neural Networks (ANN)**

28 Introduction to ANN

29 PyTorch ANN Syntax

30 What Are Activation Functions Theory

31 More on Backpropagation

32 Bringing Them Together

33 Setting Up ANN Analysis with PyTorch

34 DNN Analysis with PyTorch

35 More DNNs

36 DNNs For Identifying Credit Card Fraud

37 An Explanation of Accuracy Metrics

**Neural Networks on Images**

38 What Are Images

39 Read in Images in Python

40 Basic Image Conversions

41 Why AI and Deep Learning

42 Artificial Neural Networks (ANN) For Image Classification

43 Deep Neural Networks (DNN) For Image Classification

**Introduction to Artificial Intelligence (AI) and Deep Learning**

44 What is CNN

45 Implement CNN on Imagery Data

46 More on CNN

47 Introduction to Transfer Learning – Theory

48 Implement CNN Using a Pre-Trained Model

Resolve the captcha to access the links!