Training stable GANs Generative Adversarial Networks, or GANs for short, are quite difficult to train in practice. This is due to the nature of GAN training where two networks compete with each other in a zero-sum game. This means that one model improves at the cost of degradation in the performance of the other model. This contest makes… Read More »
Image Synthesis using Pixel CNN based Autoregressive Generative Models Recent advances in the field of deep learning have led to the development of complex generative models that are capable of generating high quality content in the form of text, audio, pictures, videos and so on. Generative models that make use of deep learning architectures to tackle the task… Read More »
What are Autoregressive Generative Models? The term ‘autoregressive’ is taken from the field of time-series forecasting frameworks. Where, In order to make a future prediction, a model considers all the past observations in a timely manner. Autoregressive generative models are also quite similar in nature. They also take help from all their past predictions in order to decide… Read More »
Building blocks of deep generative models In this article, we will learn about some important concepts that are important to learn if we want to thoroughly understand how a deep generative learning model works. We will learn about some probabilistic concepts that help the generative learning frameworks in learning data distributions. These concepts are basic building blocks of… Read More »
Generative Learning refers to a special class of statistical models that are capable ofgenerating content that is very hard to distinguish from the reality (or fake content thatlooks real). The generated content could be poems, images, music, songs, videos, 3Dobjects or content from some other domain we could imagine. A domain is nothing but a fancy word for… Read More »
Generative Learning and its Differences from the Discriminative Learning Generative Learning refers to a special class of statistical models that are capable ofgenerating content that is very hard to distinguish from the reality (or fake content thatlooks real). The generated content could be poems, images, music, songs, videos, 3Dobjects or content from some other domain we could imagine.… Read More »
Handwriting Recognition also termed as HTR(Handwritten Text Recognition) is a machine learning method that aims at giving the machines an ability to read human handwriting from real-world documents(images). The traditional Optical Character Recognition systems(OCR systems) are trained to understand the variations and font-styles in the machine-printed text(from documents/images) and they work really well in practice(example-Tesseract). Handwriting Recognition on… Read More »
Data is like a fuel to a Data Scientist. Any study or research work requires a good amount of quality data. The term ‘good amount of quality data’ changes with the kind of study one wants to do. Various sampling techniques are there to get you just that. As a researcher, you may want to study-different animals, changing… Read More »
As data scientists, we come across numerous classification problems every once in a while. Ensemble learning techniques like bagging and boosting typically give us quite high classification performances. But all such models are much complex and hard to interpret. To make sure that everything is working fine and also to understand the prediction results/logic better, it becomes necessary… Read More »
OpenCV-AI-toolkit was first introduced nearly 20 years ago(in 1999) by Intel Research and it is getting richer and better every year since then. OpenCV was primarily written in C++ language but has bindings for Python, Java, and MATLAB that makes it easy to integrate into different ML/AI projects. You will find almost every Computer Vision(Computer Graphics based) project… Read More »