CaptionsMaker
.com
Transfer Learning | Lecture 9
Edit Subtitles
Download Subtitles
SRT
TXT
Title:
Description:
Let's talk about the fastest and easiest way you can build a deep learning model, without worrying too much about how much data you have. Deep Learning Crash Course playlist: https://www.youtube.com/playlist?list=PLWKotBjTDoLj3rXBL-nEIPRN9V3a9Cx07 References and further reading: CS231n: Convolutional Neural Networks for Visual Recognition http://cs231n.github.io/transfer-learning/ Best Practices for Fine-tuning Visual Classifiers to New Domains http://adas.cvc.uab.es/task-cv2016/papers/0002.pdf How transferable are features in deep neural networks? https://arxiv.org/pdf/1411.1792.pdf What makes ImageNet good for transfer learning? https://arxiv.org/pdf/1608.08614.pdf ImageNet http://www.image-net.org/ How neural networks build up their understanding of images https://distill.pub/2017/feature-visualization/ Distilling the Knowledge in a Neural Network https://arxiv.org/pdf/1503.02531.pdf #deeplearning #machinelearning
YouTube url:
https://www.youtube.com/watch?v=_2EHcpg52uU
Created:
26. 6. 2020 11:32:19