Handwritten digit recognition using CrysX-NN neural network trained on MNIST_Plus
In the last post, I showcased an app based on a neural network, trained on the MNIST dataset using the CrysX-NN library. The…
Read More
Author: Manas Sharma
PhD researcher at Friedrich-Schiller University Jena, Germany. I'm a physicist specializing in theoretical, computational and experimental condensed matter physics. I like to develop Physics related apps and softwares from time to time. Can code in most of the popular languages. Like to share my knowledge in Physics and applications using this Blog and a YouTube channel.
Handwritten digit recognition using CrysX – Neural Network library and Streamlit Web App
Recently, I wrote a blog post on creating a Streamlit app for recognizing handwritten digits using a convolutional neural network model with the…
Read More
Digit recognition App (Streamlit) trained on the MNIST_Plus dataset using PyTorch CNN model
In my previous blog post, I shared with you a streamlit app that recognizes handwritten digits entered by the user through mouse/touch input.…
Read More
Streamlit App for Digit recognition trained on the MNIST dataset using PyTorch
Recently, I learned how to program deep and convolutional neural networks using various frameworks like PyTorch and TensorFlow-Keras. Here is an application of…
Read More
Mean Squared Error loss function and its gradient (derivative) for a batch of inputs [Python Code]
In this post, I show you how to implement the Mean Squared Error (MSE) Loss/Cost function as well as its derivative for Neural…
Read More
Efficient implementation of Tanh activation function and its Derivative (gradient) in Python
The mathematical definition of the Tanh activation function is and its derivative is defined as The Tanh function and its derivative for a…
Read More
Efficient implementation of Softplus activation function and its Derivative (gradient) in Python
The mathematical definition of the Softplus activation function is with the derivative defined as , which is actually the Sigmoid function. We have…
Read More
Efficient implementation of Softmax activation function and its Derivative (jacobian) in Python
The mathematical definition of the Softmax activation function is with the derivative defined as The Softmax function and its derivative for a batch…
Read More
Efficient implementation of Sigmoid activation function and its Derivative (gradient) in Python
The mathematical definition of the Sigmoid activation function is and its derivative is The Sigmoid function and its derivative for a batch of…
Read More
Efficient implementation of ReLU activation function and its Derivative (gradient) in Python
The mathematical definition of the ReLU activation function is and its derivative is defined as The ReLU function and its derivative for a…
Read More