
Hacking an Artificial neural network
They also have a weak spot — they can be hacked! Adversarial attacks, where inputs are tweaked to mislead these networks, have become a concern. In this post, we’ll explore the basics of hacking neural networks in a responsible and ethical manner. What is it? The FGSM (Fast Gradient Sign Method) is a type of attack that falls…

Swish Activation function
The smooth and nonmonotonic function that can be used in place of the commonly used ReLU activation function. Introduction to Activation Functions In machine learning and deep learning, an activation function is a mathematical function that is applied to the output of a neural network layer to introduce nonlinearity into the network, allowing it to…

Entropy and Information gain
Photo by Kyle Roxas Some moments occur when we notice that we have seen this term somewhere and we don’t remember what it exactly means. Entropy and information gain belong to the same categories of terminologies. We will try to understand entropy and information gain in a very simple and uncomplicated way. A basic understanding…

Shout out to GAN (Start ver.)
Writing after a long time, Here’s the basic + indepth mix explanation of Generative adversarial networks and StyleBased Generative Adversarial networks. Introduction GAN is simply a generative model that generates new data from the input data. They are used to perform unsupervised operations. They work majorly with image data and also audio data. The Generative…

Logistic regression (Lucid Explanation)
Let’s understand the logistic regression without any elaboration and in a short manner, that won’t waste your time rather than it will deliver you just the needed information. So don’t even have a cup of coffee with you, before sipping the coffee you’ll grasp logistic regression. Introduction Logistic regression is the foundational algorithm essential for…