Using ReLU, Sigmoid and Tanh with PyTorch, Ignite and Lightning
Rectified Linear Unit, Sigmoid and Tanh are three activation functions that play an important role in how neural networks work....
Tag: deep learning
Binary Crossentropy Loss with PyTorch, Ignite and Lightning
Training a deep learning model is a cyclical process. First, you feed forward data, generating predictions for each sample. Then,...
Object Detection for Images and Videos with TensorFlow 2.0
Object detection is one of the areas in Deep Learning where much progress has been made. Using a variety of...
Getting started with PyTorch
When you want to build a deep learning model these days, there are two machine learning libraries that you must...
Using SELU with TensorFlow 2.0 and Keras
Neural networks thrive on nonlinear data only when nonlinear activation functions are used. The Rectified Linear Unit, or RELU, is...
Bidirectional LSTMs with TensorFlow 2.0 and Keras
Long Short-Term Memory networks or LSTMs are Neural Networks that are used in a variety of tasks. Used in Natural...
Build an LSTM Model with TensorFlow 2.0 and Keras
Long Short-Term Memory (LSTM) based neural networks have played an important role in the field of Natural Language Processing. In...
ALBERT explained: A Lite BERT
Transformer models like GPT-3 and BERT have been really prominent in today’s Natural Language Processing landscape. They have built upon...
Differences between Autoregressive, Autoencoding and Sequence-to-Sequence Models in Machine Learning
Transformers have changed the application of Machine Learning in Natural Language Processing. They have replaced LSTMs as state-of-the-art (SOTA) approaches...
A gentle introduction to Long Short-Term Memory Networks (LSTM)
One of the fields where Machine Learning has boosted progress is Natural Language Processing. This is particularly true for the...
