PinnedPublished inTowards AIGradient Descent OptimizationGradient Descent Optimization AlgorithmsOct 18, 2022Oct 18, 2022
PinnedPublished inTowards Data ScienceIntriguing Properties of Neural NetworksHow do Neural Nets Work?May 18, 2022May 18, 2022
PinnedPublished inTowards Data ScienceQRNN: A Potential Competitor to the TransformerTraining Faster RNNs with Quasi-RNNOct 7, 20201Oct 7, 20201
PinnedPublished inTowards Data ScienceA Comprehensive Guide to Generative Adversarial Networks (GANs)Generating Meaningful Data from NoiseMay 16, 2020May 16, 2020
Published inTowards Data ScienceUnderstanding LoRA Part I: Exploring Intrinsic DimensionsEfficient fine-tuning techniques for Language ModelsOct 311Oct 311
Published inThe StartupMy 2-Time Google Foobar ExperienceHow I did at the Google Foobar Challenge, Twice!Jan 26, 20211Jan 26, 20211
Published inTowards Data ScienceGPT-3 ExplainedUnderstanding Transformer-Based Self-Supervised ArchitecturesJan 12, 2021Jan 12, 2021
Published inTowards Data ScienceDynamic Programming in RLTowards Training Better Reinforcement Learning AgentsDec 30, 2020Dec 30, 2020
Published inTowards Data ScienceLongformer: The Long-Document TransformerUnderstanding Transformer-Based Self-Supervised ArchitecturesDec 1, 20201Dec 1, 20201
Published inTowards Data ScienceOptimizing Model Training with TensorFlow ProfilerOptimizing GPU Performance with TensorFlowNov 13, 2020Nov 13, 2020
