Dhruv Nair

In this post, we will showcase a Custom Panel dedicated to debugging object detection models. We will use the Penn-Fudan Pedestrian Detection dataset, along with a Faster-RCNN model, with a Resnet5...

Machine Learning models tend to perform inconsistently across different parts of a dataset. Summary performance metrics such as AUC, and F1, are not enough to identify the parts of the data where a model need...

Hugging Face provides awesome APIs for Natural Language Modeling. In particular, they make working with large transformer models incredibly easy. These models can be used off-the-shelf for text generation, translation, an...

Introduction 3D Histograms or Ridge Plots are a great way to visualize the training progress of your Neural Network. Histogram distributions of the weights, gradients, and activations allow us to g...

Introduction A confusion matrix is a visual way to inspect the performance of a classification model. Metrics such as accuracy can be inadequate in cases where there are large class imbalances in the data, a p...

Introduction Model training is arguably the most time consuming, and computationally demanding part of the Machine Learning pipeline. Depending on the complexity of your model, or search space, it ...

  Check out part 1 (here)and part 2 (here) of this series In the last part of our series on uncertainty estimation, we addressed the limitations of approaches like bootstrapp...

  You can check out part 1 of this series here In part 1 of this series, we discussed the sources of uncertainty in machine learning models, and techniques to quantify u...

  “We demand rigidly defined areas of doubt and uncertainty!” - Douglas Adams, The Hitchhiker’s Guide to the Galaxy Why is uncertainty important? Let’s imag...

  R2D2 Meta-Learning Method. Full paper here Interview by Cecelia Shao The ...

Our second post in this series, where the Comet.ml team competes to win the Kaggle Home Credit Def...

Follow along as the Comet.ml team competes to win the Kaggle Home Credit Default Competition�...

TLDR: In this post, we will examine how a simple model, fastText, learns to represent entities in a subset of the FB15K kn...