Marina FusterCross-Entropy Loss for Next Token Prediction in TransformersIn light of the tremendous success of transformers in the context of the Next Token Prediction task, I’ve decided to create this post to…4d ago
Jason McEweninTowards Data ScienceDifferentiable and Accelerated Spherical Harmonic TransformsIn JAX and PyTorchMar 141
Sushmita PoudelRecurrent Neural Network (RNN) Architecture ExplainedThis article will provide insights into RNNs and the concept of backpropagation through time in RNN, as well as delve into the problem of…Aug 28, 20234Aug 28, 20234
Racha SalhiIntroduction To Neural Networks — Part 3Neural network implementation from scratch using Python, without any deep learning framework.4d ago4d ago
AmanatullahVanishing Gradient Problem in Deep Learning: Understanding, Intuition, and SolutionsIntroductionJun 12, 2023Jun 12, 2023
Marina FusterCross-Entropy Loss for Next Token Prediction in TransformersIn light of the tremendous success of transformers in the context of the Next Token Prediction task, I’ve decided to create this post to…4d ago
Jason McEweninTowards Data ScienceDifferentiable and Accelerated Spherical Harmonic TransformsIn JAX and PyTorchMar 141
Sushmita PoudelRecurrent Neural Network (RNN) Architecture ExplainedThis article will provide insights into RNNs and the concept of backpropagation through time in RNN, as well as delve into the problem of…Aug 28, 20234
Racha SalhiIntroduction To Neural Networks — Part 3Neural network implementation from scratch using Python, without any deep learning framework.4d ago
AmanatullahVanishing Gradient Problem in Deep Learning: Understanding, Intuition, and SolutionsIntroductionJun 12, 2023
Long NguyenBuilding a Recurrent Neural Network From ScratchIn this blog post, we will explore Recurrent Neural Networks (RNNs) and the mathematics behind their forward and backward passesJan 28
AlMoonlightUnderstanding the Intricate Math Behind Neural Networks in Machine LearningWhat is a neuron ?Jul 24