Learn how to achieve good accuracy on a classification task with just a few samples per class and imbalanced distribution of classes



Nowadays there are several deep learning models like BERT, GANs, and U-Nets that are achieving a state-of-the-art performance of tasks like image recognition, image segmentation, and language modeling. Hardly a day goes by without a new innovation in Machine Learning. Tech Giants like Google, Microsoft, and Amazon are coming up with complex deep learning architectures that achieve human-like performance. But one problem with these models is that they require a ton of labeled data. Sometimes much data is not available for a specific task. Less data means the deep learning model will not be able to model different classes properly…


TensorBoard is a tool that provides measurements and visualizations needed during machine learning workflow.

In this tutorial, I will give a quick tutorial on how to visualize your feature vectors on TensorBoard. Using a machine learning model, sometimes we want to learn embeddings of different classes. Embeddings are a way to map different inputs like (images, text, etc) to multi-dimensional vectors. Using TensorBoard, you can visualize the representations or feature vectors. You can also visualize the input data directly. TensorBoard also provides dimensionality reduction methods like PCA and t-SNE. …

Aditya Dutt

Machine Learning PhD Student at University of Florida

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store