InTDS ArchivebyKai Xin Thia·Apr 10, 2020The Future of Visual Recommender Systems: Four Practical State-Of-The-Art TechniquesThe future of visual RecSys is an exciting one. Let us explore some of the most cutting edge techniques and ideas that we can incorporate…
InTDS ArchivebyKai Xin Thia·Apr 5, 2020Temporal Fashion RecommenderBuilding a Recommender That Evolves with Seasons
InTDS ArchivebyKai Xin Thia·Mar 28, 2020Building a Personalized Real-Time Fashion Collection RecommenderWe will make use of transfer learning, approximate nearest neighbors, and embeddings centroid detection in PyTorch to build our…A response icon3A response icon3
InAnalytics VidhyabyKai Xin Thia·Mar 21, 2020COVID-19 Case Study with CNNWe will cluster COVID-19 X-ray images based on severity with our CNN RecSys flow using transfer learning, Spotify’s Annoy, and PyTorchA response icon1A response icon1
InAnalytics VidhyabyKai Xin Thia·Mar 20, 2020Convolutional Neural Networks RecommenderWe will build a recommender by leveraging transfer learning with ResNet and return visually similar products across 240K images within 2ms
InAnalytics VidhyabyKai Xin Thia·Mar 12, 2020Intro to Visual RecSysWe will explore the “hello world” data for visual models, the FashionMNIST dataset from Zalando with PyTorch, Tensorboard and Colab.
InAnalytics VidhyabyKai Xin Thia·Mar 4, 2020How to Design a Recommender?For this chapter, I will introduce the RecSys Design Framework with a case study of Amazon.A response icon1A response icon1
InArtificial Intelligence in Plain EnglishbyKai Xin Thia·Feb 26, 2020How does a recommender work?In this series of articles, I will introduce modern approaches to visual recommender systems. We begin with a case study of Spotify.
Kai Xin Thia·May 30, 2018How to create differentiating products in the face of AI democratizationI have the privilege of hosting Avi (VP — Data Sciences, AI & ML, InMobi), Hong Ting (CEO and Cofounder, Botbot.AI) and Kenny (Head of R&D…