CNN implementation for medical X-Ray image segmentation

Find logos in images and videos in just one-shot. Never be embarrassed again to say that you have a small data situation!

TensorFlow Input Pipeline Examples based on multi-thread and FIFOQueue

finetune bert for small dataset text classification in a few-shot learning manner using ProtoNet

PyTorch implementation of Sentiment Analysis of the long texts written in Serbian language (which is underused language) using pretrained Multilingual RoBERTa based model (XLM-R) on the small dataset.

Generative Latent Implicit Conditional Optimization when Learning from Small Sample ICPR 20'

Sentiment Analysis of tweets written in underused Slavic languages (Serbian, Bosnian and Croatian) using pretrained multilingual RoBERTa based model XLM-R on 2 different datasets.

AutoML tool for imbalanced and small tabular datasets

Project to scrape CFTC.gov reports and present using Power Query & Power Pivot

This repository contains Alzheimer's detection model using few-shot learning and a machine learning ensemble model. With limited samples, the few shot learning enables efficient detection and the ensemble model incorporates the advantages of multiple algorithms improving the efficiency of detection.

Mixture of Experts from scratch

My solution of dirty/cleaned plates recognition kaggle task

Experiments with artificial neural networks on small datasets.

Research log for Clastic Music

A deep learning based domain knowledge integration for small dataset

Cancer detection through a blood test (CancerSEEK) using machine learning techniques.

A dataset for 12 Iranian weed species is provided and several Deep Learning pre-trained models are utilized for the multi-class classification task.

Homework on training deep networks with very small data - MVA MSc

Attempt to predict the median price of homes in a given Boston suburb in the mid-1970s, given data points about the suburb at the time, such as the crime rate, the local property tax rate, and so on. Only 506 data points, split between 404 training samples and 102 test samples. Each feature in the input data (for example, the crime rate) has a d…