Contrastive Representation Learning by Lilian Weng – Link Understanding Contrastive Learning (Learn how to learn without labels using self-supervised learning) – Link Supervised Contrastive Learning by Prannay Khosla et. al @NeurIPS 2020 – Link Extending Contrastive Learning to the Supervised Setting by AJ Maschinot et. al. – Link
Deep Learning on the Edge
How do we Optimize Deep Learning models for edge devices? Training a single AI model can emit as much carbon as five cars in their lifetimes Parameter Removal: Identify the trainable layers in the model and reduce the number of parameters! Weight Pruning: Specific connections between neurons are removed. In practice this removal means replacing…
PyTorch
Pytorch Hooks How to Use PyTorch Hooks by Frank Odom @MediumUnderstanding Hooks by Ayoosh Kathuria @Paperspace Best Practices / Tips & Tricks 7 Tips To Maximize PyTorch Performance by William Falcon @Towardsdatascience
Explainable Neural Networks
Explainable Neural Networks: Recent Advancements, Part 1 Explainable Neural Networks: Recent Advancements, Part 2 Explainable Neural Networks: Recent Advancements, Part 3 Network In Network by Min Lin 2013 Gradient Based Approaches Visualizing Gradients (2014) In the paper “Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps“ Karen Simonyan et. al. proposed two visualisation…
Interpretable Machine Learning
Books Interpretable Machine Learning: A Guide for Making Black Box Models Explainable by Christoph Molnar Papers Doshi-Velez, Finale, and Been Kim. “Towards a rigorous science of interpretable machine learning” 2017.
Buzzwords
Domain Randomization
Domain Randomization: future of robust modeling by Urwa Muaz Invariance, Causality, and Robust Deep Learning – Why do Neural networks fail to generalize to new environments, and how can this be fixed? by by Urwa Muaz
Important Concepts in Deep Learning
Chromosome Segmentation in Pytorch using U-Net Architecture
Details about the usecase can be studied from the references given below in the references section. Following is the source code. The code was run on Google Colab. Imports & Utilities Importing the Libraries Following is the code to set device based on the type of machine (CPU or GPU). Following is the code for…
Must Read Papers
Neural Architecture Search Neural Architecture Search: A Survey – Thomas Elsken Literature on Neural Architecture Search Transfer Learning & Domain Adaptation Model Compression – Cristian Bucila˘ et. al. – KDD 2006 A Survey on Transfer Learning – Sinno Jialin Pan, et. al. – 2010 Unbiased look at dataset bias – Antonio Torralba et. al. –…