How to use L1, L2 and Elastic Net regularization with PyTorch?
Training a neural network means that you will need to strike a balance between optimization and over-optimization. Over-optimized models work...
Category: Deep learning
How to create a neural network for regression with PyTorch
In many examples of Deep Learning models, the model target is classification – or the assignment of a class to...
How to use PyTorch loss functions
Loss functions are an important component of a neural network. Interfacing between the forward and backward pass within a Deep...
Building a simple vanilla GAN with PyTorch
Using a Generative Adversarial Model, or a GAN, it is possible to perform generative Machine Learning. In other words, you...
Creating DCGAN with TensorFlow 2 and Keras
Generative Machine Learning is a really interesting area of research that investigates how Machine Learning (and by consequence, Deep Learning)...
Creating DCGAN with PyTorch
Generative Adversarial Networks have been able to produce images that are shockingly realistic (think This Person Does Not Exist). For...
Easy grammar error detection & correction with Machine Learning
Machine learning in general and deep learning in particular has boosted Natural Language Processing. A variety of models has allowed...
Convolutional Neural Networks with PyTorch
Deep neural networks are widely used to solve computer vision problems. Frequently, their performance is much better compared to Multilayer...
Using Dropout with PyTorch
The Dropout technique can be used for avoiding overfitting in your neural network. It has been around for some time...
Batch Normalization with PyTorch
One of the key elements that is considered to be a good practice in a neural network is a technique...
