Reinforcement Learning with Augmented DataOutline The main idea inferred in this paper is by simple data augmentation the efficiency of a model (can we just maximize the rewards). This method was to counterbalance the current issues in RL; i.e.; data-efficiency of learning and generalization...May 18, 2022 · 3 min readsajal-tiwari.hashnode.dev
Deep image reconstruction from human brain activityOutline This research paper explains and compares the way humans perceive images and try to replicate them through Deep Neural networks (DNN). The basic idea here is to read the thoughts of humans through fMRI and then visualize them to create or pre...1MMay 18, 2022 · 2 min readsajal-tiwari.hashnode.dev
Do ImageNet Classifiers Generalize to ImageNet ?Do ImageNet Classifiers Generalize to ImageNet ? Outline The Idea behind this paper is to check weather the ImageNet Classifiers classifies the image from another test set with same linearity or over the years training on ImageNet data has led to ove...May 12, 2022 · 4 min readsajal-tiwari.hashnode.dev