Abhishek Mishra

Algorithm design, System Architecture and Technology

Articles by Abhishek Mishra

Why do you need a Fully Connected Layer?

        A Fully connected layer is the actual component that does the discriminative learning in a Deep Neural Network. It’s a simple Multi layer perceptron that can learn weights that can identify an object class. You can read about MLP in any ML text book.   If you take a simple 1-2 layer neural network the weights are learned so that an input...
2 months 7 hours ago

Image Matting using Machine Learning

Image matting is an interesting problem in computer vision that deals with identifying the foreground and background components of an image. While this may seem a fairly easy task, sometimes even experienced graphics professional find it difficult. Lets see the very famous example of dandelion image. Our task is to separate the background (green)...
1 year 1 month ago

Computer Vision in AI - Facts to think about

Artificial Intelligence (AI) is the buzzword of this decade. Google, Facebook, Twitter and IBM are acquiring companies and people as fast as they can. Computer Vision is one of the core focus areas. Vision is perhaps one of the most difficult problems to solve in AI, and as you might have guessed, it is currently unsolved.   Neural Networks,...
1 year 1 month ago
Machine Learning, Step Size

Machine Learning Concept - Step Size

At Numahub, training models is something we do more times in a week than having dinners with our better halves. While working with machine learning algorithms, especially the ones which use Gradient Descent for optimization, we often come across “step size”.  If you are a Machine Learning enthusiast I am pretty sure you would have come across this...
1 year 8 months ago