Dhruv MataniinTowards Data ScienceInterpreting Weight Regularization In Machine LearningWhy do L1 and L2 regularization result in model sparsity and weight shrinkage? What about L3 regularization? Keep reading to find out more!Aug 231Aug 231
Dhruv MataniinTowards Data ScienceChallenges of Detecting AI-Generated TextWe’ll take an in-depth look at the challenges of detecting AI-generated text, and the effectiveness of the techniques used in practice.Sep 27, 20231Sep 27, 20231
Dhruv MataniinTowards Data ScienceLanguage Models for Sentence CompletionA practical application of a language model that picks the most likely candidate word that extends an English sentence by a single wordSep 15, 2023Sep 15, 2023
Dhruv MataniinTowards Data ScienceTensor Quantization: The Untold StoryA close look at the implementation details of quantization in machine learning frameworksSep 8, 20233Sep 8, 20233
Dhruv MataniinTowards Data ScienceEfficient Image Segmentation Using PyTorch: Part 4A Vision Transformer-based modelJun 27, 20232Jun 27, 20232
Dhruv MataniinTowards Data ScienceEfficient Image Segmentation Using PyTorch: Part 3Depthwise separable convolutionsJun 27, 2023Jun 27, 2023
Dhruv MataniinTowards Data ScienceEfficient Image Segmentation Using PyTorch: Part 2A CNN-based modelJun 27, 2023Jun 27, 2023
Dhruv MataniinTowards Data ScienceEfficient Image Segmentation Using PyTorch: Part 1Concepts and IdeasJun 27, 2023Jun 27, 2023
Dhruv MataniinTowards Data ScienceNT-Xent (Normalized Temperature-Scaled Cross-Entropy) Loss Explained and Implemented in PyTorchAn intuitive explanation of the NT-Xent loss with a step-by-step explanation of the operation and our implementation in PyTorchJun 13, 2023Jun 13, 2023
Dhruv MataniAll Pairs Cosine Similarity in PyTorchPyTorch defines a cosine_similarity function to compute pairwise cosine similarity between pairs of vectors. However, there’s no method to…Jun 8, 20232Jun 8, 20232