Thimira Amaratunga's research while affiliated with Sri Lanka Army and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (13)
We are now ready to start building our first deep learning model.
As you have probably learned by now, training deep learning models can take long times: hours and maybe days, based on how complex the model and how large your dataset.
In Chapter 1, we briefly touched upon the concept of reinforcement learning. As we discussed there, reinforcement learning is one of the methods in which machine learning models are trained.
Now that we know what we need to get started, let us begin setting up our tools.
Running our first deep learning model gave us a small glimpse of what deep learning can do. There are many exciting projects we can build with deep learning.
We have talked about the ways in which deep learning and computer vision go together. In the past few chapters, we have built some computer vision models: deep learning image classification models, from handwritten digit classification to bird identification. In Chapter 3, when we set up our deep learning development environment, we installed sever...
Over the past several chapters, we have talked about some techniques to optimize the training of a model. We went through the steps of starting with a small dataset to get results that can be applied in practical scenarios.
We saw how exceptionally well deep learning models performed when applied to computer vision and classification tasks. Our LeNet model with the MNIST and Fashion-MNIST datasets was able to achieve 90%–99% accuracy under a very reasonable amount of training time. We have also seen how the ImageNet models have achieved record-breaking accuracy levels...
Can an AI be creative—can it learn to create art, for example? The traditional answer was no. But lately we are not so sure. Recently, thanks to deep learning, the definition of creativity has been become blurred.
When building a deep learning model, it is often better to be able to visualize the model. Although the model we created—the LeNet model—is simple, it is better if we can see the structure. Especially when we are tweaking or modifying the model, we can easily compare their structures. And when working with more complex models (which we will look at...
Welcome to the exciting world of deep learning, AI, and computer vision.
Build deep learning and computer vision systems using Python, TensorFlow, Keras, OpenCV, and more, right within the familiar environment of Microsoft Windows. The book starts with an introduction to tools for deep learning and computer vision tasks followed by instructions to install, configure, and troubleshoot them. Here, you will learn how Pytho...
