Neural Encoders: From Autoencoders to Modern Retrieval ArchitecturesNeural encoders are sophisticated neural networks that transform diverse inputs — including text, images, and audio — into dense numeric…Apr 19Apr 19
Scaling AI Teams and WorkloadFeature-Based Scaling: Many software systems scale by organizing teams around specific features. For instance, a plugin framework enables…Apr 18Apr 18
Creating a Tiny VectorDB, Part 1Learn how a vector database quickly finds nearest neighbors with graph algorithms.Apr 17, 2024A response icon1Apr 17, 2024A response icon1
Keeping Up with RAGs: Recent Developments and Optimization TechniquesRAG is layer over vanilla LLMs to help infuse external knowledge and generate human-like response to your query, grounded on set of…Mar 15, 2024Mar 15, 2024
External Knowledge in LLMsLLMs are trained on finite set of data. While it can answer wide variety of questions across multiple domain, it often fails to answer…Mar 9, 2024Mar 9, 2024
Speed up your Keras Sequence PipelineUsing shared memory to optimize the pipelines blocked by GIL in python 3.8 and tensorflow 2.3Apr 9, 2022Apr 9, 2022
LinkedIn Data Science Interview QuestionsI recently interviewed for a research engineer (vision) role at LinkedIn. In this role the candidate is expected to work on state-of-the…Jan 8, 2022A response icon2Jan 8, 2022A response icon2
