Limarc is a Tokyo-based writer of all things pop culture, travel, and tech.
Whether you’re a beginner looking for introductory articles or an intermediate looking for datasets or papers about new AI models, this list of machine learning resources has something for everyone interested in or working in data science. In this article, we will introduce guides, papers, tools and datasets for both computer vision and natural language processing.
Machine Learning Resources for Computer Vision
Data scientists working in computer vision are developing machines that can see the world and process visual data similar to the way the human mind processes visual data. Without the developments and breakthroughs in computer vision, self-driving cars, facial recognition, and virtual reality headsets wouldn’t be possible today.
Below are just a few of the best computer vision articles, papers, tools, and datasets for beginners, intermediates, and experts in the field.
5. Kornia - From researchers at the Cezch Technical University at Prague and Open CV, this paper introduces Kornia, an open source computer vision library for PyTorch.
6. Mask R-CNN - In this paper, researchers at Facebook AI present Mask R-CNN, a framework for object image segmentation.
7. Intro to CNN Keras - While not published in an official academic journal, the Intro to CNN Keras is one of the most popular notebooks on Kaggle. The notebook details a step-by-step guide on how to train a convolutional neural network for digit recognition.
Computer Vision Tools
8. CVAT - CVAT stands for Computer Vision Annotation Tool, and is an online platform for labelling images and videos.
9. VGG Image Annotator - An open source image annotation tool that supports bounding boxes, polygons, circles, ellipticals, keypoints, and polylines.
Datasets for Computer Vision
10. Open Images Dataset - From Google, the Open Images Dataset is one of the largest publicly available image datasets in the world. It includes millions of images with accompanying annotations.
11. COCO - The COCO dataset includes over 333,000 images and with around 183,000 of those images labeled. Within the images, 1.5 million objects have been annotated.
Machine Learning Resources for NLP
Natural language processing (NLP) is the field of machine learning that seeks to give computers the ability to understand written and spoken languages. It is thanks to developments in NLP that we have virtual assistants, smart home devices, voice search engines, and other amazing technologies.
Below are just a few of the best NLP articles, papers, tools, and datasets.
12. Your Guide to NLP - A beginner’s guide to understanding the basic concepts of natural language processing, use cases, and essential NLP terms.
We hope one of the machine learning resources on this list helped you learn something new, or helped contribute to your machine learning projects. New interesting ML papers and open-source tools are constantly being released. Please follow me on Hackernoon for further updates.