Have you ever wondered how a product recommender is built? How you can infer the underlying sentiment from reviews? How you can extract information from images to find visually-similar products to recommend? How you construct an application that does all of these things in real time, and provides a front-end user experience? That’s what you will build in this course!
Using what you’ve learned about machine learning thus far, you will build a general product recommender system that does much more than just find similar products You will combine images of products with product descriptions and their reviews to create a truly innovative intelligent application.
You’ve probably heard that Deep Learning is making news across the world as one of the most promising techniques in machine learning, especially for analyzing image data. With every industry dedicating resources to unlock the deep learning potential, to be competitive, you will want to use these models in tasks such as image tagging, object recognition, speech recognition, and text analysis. In this capstone, you will build deep learning models using neural networks, explore what they are, what they do, and how. To remove the barrier introduced by designing, training, and tuning networks, and to be able to achieve high performance with less labeled data, you will also build deep learning classifiers tailored to your specific task using pre-trained models, which we call deep features.
As a core piece of this capstone project, you will implement a deep learning model for image-based product recommendation. You will then combine this visual model with text descriptions of products and information from reviews to build an exciting, end-to-end intelligent application that provides a novel product discovery experience. You will then deploy it as a service, which you can share with your friends and potential employers.
Learning Outcomes: By the end of this capstone, you will be able to:
-Explore a dataset of products, reviews and images.
-Build a product recommender.
-Describe how a neural network model is represented and how it encodes non-linear features.
-Combine different types of layers and activation functions to obtain better performance.
-Use pretrained models, such as deep features, for new classification tasks.
-Describe how these models can be applied in computer vision, text analytics and speech recognition.
-Use visual features to find the products your users want.
-Incorporate review sentiment into the recommendation.
-Build an end-to-end application.
-Deploy it as a service.
-Implement these techniques in Python.