

Artificial Intelligence image recognition -How we're teaching computers :
The field of Artificial Intelligence and deep learning has bloomed beautifully in the last decade. It gave birth to the state of the art computer vision techniques. This encouraged innovation of many useful gadgets. We have developed cameras with jaw-dropping shutter speeds and color qualities. Moreover, we’re successful in reducing the size of these cameras. We can even fit them in pens!
Despite that, cameras still lack the basic ‘intelligence’ that can distinguish basic things such as a normal circle and a soccer ball. Fei Fei Li is a pioneer in this field. Researchers know her for her immense contribution in the field image recognition and computer vision. She explains about things such as developments in the field. And how scientists are working to make cameras understand the pictures.
Why is Computer Vision ‘Blind’? : Artificial intelligence Image recognition
You might wonder that if cameras can even capture detailed surfaces Mars and Moon, then what’s the next big thing in this field? As mentioned above, cameras need to understand what’s going on in the pictures. Cameras without artificial intelligence can’t point out the differences between a completely black picture and scenery, and that is very similar to blindness as they can draw any perception from imagery.
Machine learning engineers have been devising ways to train computers to identify objects by developing complex mathematical models and algorithms. However, Fei Fei Li observed that instead of focusing solely on algorithms, we should also pay attention to the type of image data on which the model will be trained.
Why is Computer Vision ‘Blind’?
You might wonder that if cameras can even capture detailed surfaces Mars and Moon, then what’s the next big thing in this field? As mentioned above, they need to understand what’s going on in the pictures. Cameras without artificial intelligence can’t point out the differences between a completely black picture and scenery. This is very similar to blindness as they can draw any perception from imagery.
Machine learning engineers have been devising ways to train computers to identify objects by developing complex mathematical models and algorithms. However, Fei Fei Li observed that we should not focus solely on algorithms. Instead, we should also pay attention to the type of image data for training the model.
The breakthrough in Computer Vision
In 2009, around 50,000 workers across the globe started working on Fei Fei’s idea of a large and comprehensive dataset. This is the world famous project - ImageNet. It has 15 million images and 22 thousand object classes. The reason behind making this versatile and huge dataset was to imitate the data in mind of a 3-year-old child. This mimics the training of an infant’s mind which is very similar to neural networks.
Researchers began training a CNN model on the given data. They followed the approach suggested by Geoffrey Hinton back in the 1980s. Just like the human brain, CNN has nodes and stacked up layers in which the data flows over iterations. The CNN based on ImageNet had 24 million nodes & 15 billion connections.
Surprisingly, this model was very accurate in classifying multiple objects, even in complex images. Back then, it was a state of the art algorithm and model which won many competitions. The best part is that the general public can download ImageNet, that too free of cost!
So, what’s next?
Google’s Street View uses ImageNet to gain deep insights. For instance, it draws a correlation between the car prices and location, crime rates, zip codes etc. However, it only covers object detection and recognition.
Computer scientists have been using CNNs for image recognition. They are combining them with RNNs to perform tasks of NLP. As a result, we can see their uses in a lot of domains such as image captioning, robotics, drones and a wide range of educational/security gadgets.
This field has made significant progress. But computers are still susceptible to mistakes. Even though we’ve come very far in the last few years, there's still a long way to go.
WATCH LIVE CLASSES FREE
Learn from Leading Experts | Learn by Doing
$12.50/month$24.95/month
$149.95/year$239.95/year
(with discounts)
Save even more for teams!
Find out more...


The organization clearly has great client relationships, and a facility for working with subject matter experts that is second to none.


I have worked in the machine learning field for many years and I am very impressed by the quality of ML and AI training that the Starweaver team team delivers. The entire team is just great.


Starweaver and I have collaborated on cybersecurity training initiatives for the past three years. The work together is excellent and interesting. Their training management is exceptional.


I completed an excellent and hands on training course in Azure. The team driven Comp Case required a lot of work but also had us applying everything we learned week after week. The course was the best!


Starweaver’s program management and curriculum design team very clearly and consistently lays-out road maps around likely pain points. Excellent to work with.


I cannot stress how amazing this Azure bootcamp was for me and my colleagues. The project and team assignments were excellent.


👍👍👍👍👍 The Azure certification course is helping me to have a solid understanding of how the platform works. Thanks to the team for demonstrating you really care about us.


Great cloud course on Azure run by super capable instructors live online. The Comp Case was a great exercise we had to work on in virtual teams over weeks. I can easily say this was a great course.


A big HUG!!! You guys gave me something to really be passionate about. The machine learning course was powerful and gave me a real sense of how to apply Tensorflow, Keras and other tools on the job.


We have had a great experience working with Starweaver including on multiple live and online programs across a wide spectrum from core to advanced subjects and audiences. Perfect results.


I am participating in one of the many courses offered by Starweaver: “Python for Data Science & Machine Learning”, and I am so excited about it! Clear and simple explantions. Great instructor.


I have only positive things to say about Starweaver courses. The programme I completed was delivered by several excellent instructors with solid content and lots of interaction with the entire class.


The Starweaver approach to training delivery with hands on comp cases, teamwork and highly interactive challenging classes provides me the right tools to get measurable results.


I am participating in a live, online cloud training course. The course is really well-constructed, and the quality of content and delivery is super high. The teachers are great and we all appreciate it!!! It is as simple as that.


I took the Azure certification course and working with Starweaver was a 5-Star experience! The labs pushed me with hands on work. Instructors provided real-life elements and real-life scenarios. Highly recommended.