Free Live Session
Amazon Go - Future of Shopping


(1543 ratings)

Amazon Go: The future of shopping
Live Session to be Scheduled
I'm interested
“Sessions are fun when attended with friends”


Have you ever wondered if you could shop at your local supermarket, without having to queue at checkouts to pay for your groceries? In 2018, Amazon opened its first in the world checkout-free store named Amazon Go store.

Amazon Go store allows their customers to pick up what they want in a store and just walk out, without the need for a checkout line. Amazon Go store was first introduced in 2016 that leverages computer vision, sensor fusion, and deep learning to avoid payment checkout queues. Amazon Go technology can detect when products are taken or returned to the shelves and keeps track of them in your virtual cart.

Presently, there are 26 Amazon Go stores across four US cities; Seattle, Chicago, New York, and San Francisco. The outlets focus on pre-prepared lunches, dinner kits, ready meals---but also have a range of other grocery items. 

In this session, we are going to discuss how sensor fusion Amazon Go makes it possible to shop from the store without checking out from the store.

What you’ll learn in this session?

  1. What is Amazon Go?
  2. How does the sensor fusion Amazon Go store work?
  3. Understanding computer vision used in developing Amazon Go
  4. Computer vision applications in the real world
  5. What is YOLO?
  6. How does the YOLO algorithm work?
  7. What is Deep Learning?
  8. Understanding the difference between Machine Learning and Deep Learning
  9. Deep Learning applications

Who can attend this session?

  1. Anyone who is interested in knowing more about Amazon Go
  2. Students interested in learning neural networks and deep learning
  3. Professionals working in machine learning and deep learning
  4. Anyone who wants to learn YOLO(You only look once)

 So, let’s get started!!

Introduction to Amazon Go store - 

Amazon Go is the first store of its kind where you don’t need to check out from the store. Customers can simply enter the store using the Amazon Go app to browse and take the products they want and can leave. How cool is that? Amazon Go store is partially automated where customers don’t need to stand in a queue for check-out counters.

How does the sensor fusion Amazon Go store work?

To get started, you just need an Amazon account and a smartphone. You have to scan the app as you enter the store. You can then put away your phone and begin shopping - picking up items, putting them in a basket or in bags (without needing to scan each item). You can just simply walk out when you're finished. The money debits automatically from your amazon wallet.

You don't need to check out and you can replace items at any time.

What is Computer Vision?

Let’s first know the computer vision definition. Computer vision is a field of study focused on the problem of helping computers to see. It helps in making computers understand what is present or seen in an image.

The heart of the Amazon Go store is the deep learning for computer vision that is used to seamlessly track and estimate the intention of everyone in the store. Amazon Go store is one of the latest computer vision applications developed so far. 

You can add this Amazon Go case study as one of your computer vision projects in your portfolio.

What is YOLO?

YOLO (“You Only Look Once”) is an effective real-time object recognition algorithm that also encompasses many of the most innovative ideas coming out of the computer vision research community.

Object detection is a classical problem in computer vision where you need to recognize what and where — specifically what objects are inside a given image and also where they are in the image. The problem of object detection is much more complex than classification, which also can recognize objects but doesn’t indicate where the object is located in the image.

YOLO algorithm uses a totally different approach. YOLO object detection applies a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. 

YOLO architecture is based on CNN and anchor boxes and is proven to be an on-the-go object detection technique for widely used problems. With time, it has become faster and better, with its versions named as:

  • YOLO V1
  • YOLO V2
  • YOLO V3

How does YOLO Algorithm work?

YOLO algorithm is based on regression. So instead of selecting interesting parts of an image, it predicts classes and bounding boxes for the whole image in one run of the algorithm. We aim to predict a class of an object and the bounding box specifying object location. 

Each bounding box can be described using four descriptors -

  1. center of a bounding box (bxby)
  2. width (bw)
  3. height (bh)
  4. value cis corresponding to a class of an object (such as car, traffic lights, etc.)

Deep Learning Definition -

Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks.

Deep Learning is just a type of Machine Learning inspired by the structure of the human brain. Deep learning algorithms attempt to draw similar conclusions as humans can by analyzing the data with a given logical structure. To achieve this, CNN deep learning uses a multi-layered structure of algorithms called neural networks. In this session we’ll focus more on deep learning with python. 

Deep Learning applications -

These are some of the deep learning real-world applications.

  1. Fake news detection
  2. Amazon Go stores
  3. Automatic machine translations
  4. Personalization
  5. Demographic and election predictions

This case study can be one of the deep learning projects for your portfolio.

What are you waiting for? Book your seat today.