Predictive Analytics with PyTorch
This course covers the use of PyTorch to build various predictive models, using Recurrent Neural Networks, long-memory neurons in text prediction, and evaluating them using a metric known as the Mean Average Precision @ K.
What you'll learn
PyTorch is fast emerging as a popular choice for building deep learning models owing to its flexibility, ease-of-use and built-in support for optimized hardware such as GPUs. In this course, Predictive Analytics with PyTorch, you will see how to build predictive models for different use-cases, based on the data you have available at your disposal, and the specific nature of the prediction you are seeking to make.
First, you will start by learning how to build a linear regression model using sequential layers. Next, you will explore how to leverage recurrent neural networks (RNNs) to capture sequential relationships within text data. Then, you will apply such an RNN to the problem of generating names - a typical example of the kind of predictive model where deep learning far out-performs traditional natural language processing techniques. Finally, you will see how a recommendation system can be implemented in several different ways - relying on techniques such as content-based filtering, collaborative filtering, as well as hybrid methods.
When you are finished with this course, you will have the skills to build, evaluate, and use a wide array of predictive models in PyTorch, ranging from regression, through classification, and finally extending to recommendation systems.
Table of contents
- Version Check 0m
- Prerequisites and Course Outline 2m
- Structural and Predictive Models 5m
- Demo: Install and Setup Pytorch 3m
- Demo: Preparing Data 6m
- Demo: Building a Simple Neural Network to Perform Regression 4m
- Demo: Exploring the Diamonds Dataset 4m
- Demo: Preparing and Processing Data 4m
- Demo: Building and Training a Regression Model 6m
- Demo: Exploring and Preprocessing Data 6m
- Demo: Defining the Neural Network and Helper Functions 5m
- Demo: Building and Training Custom Neural Networks for Classification 6m
- Finding Patterns in Data 3m
- Association Rule Learning 2m
- Clustering 2m
- Content Based Approaches to Recommendations 4m
- Collaborative Filtering 3m
- Nearest Neighborhood 2m
- Matrix Factorization 6m
- Alternating Least Squares to Estimate the Ratings Matrix 4m
- Evaluation Metrics vs. Loss Metrics 2m
- Mean Average Precision @ K 6m
- Demo: Initializing the Ratings Matrix 6m
- Demo: Setting up the Neural Network 5m
- Demo: The Train Helper Function 7m
- Demo: The Evaluate Helper Function 2m
- Demo: Building and Training the Recommendation System Neural Network 2m
- Summary and Further Study 1m
About the author
Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework. After spending years working in tech in the Bay Area, New York, and Singapore at companies such as Microsoft, Google, and Flipkart, Janani finally decided to combine her love for technology with her passion for teaching. She is now the co-founder of Loonycorn, a content studio focused on providing ... more