Start-Tech Academy Blogs

Here you can find a simple explanation to Attention Mechanism in Deep Learning.

I will try to explain how I can use LSTMs and GRUs in order to implement a very basic feed forward network that can classify characters in a training set.

A blog about machine learning and other interesting deep learning projects

This is a tutorial for Pytorch beginners on how to build a feedforward neural network. The tutorial starts with a linear regression model and ends at a 2-layer feedforward neural network.

Gradient descent is the most popular optimization algorithm used in Deep Learning. It’s used to calculate parameters for many different kinds of architectures, but there are also many different variants of it. The purpose of this post is not to explain what gradient descent is

Gradient descent (GD) is an optimization algorithm that was derived by solving the quadratic programming (QP). A set of input values, an initial value for the output value, and its cost are required to implement GD, which is specified