Transfer Learning with indico - Ep. 27 Part 1 (Deep Learning SIMPLIFIED)

What is Transfer Learning? It is a way to transfer knowledge and learning from one neural network to nets in other domains. indico a group of Deep Learning innovators from Boston, MA has used Transfer Learning to build a demo on fashion-matching. This video is in two parts - Part 1 showcases Transfer Learning.

Online clothing stores typically recommend products by simply analyzing the past purchasing behaviors of their customers. Deep learning is currently revolutionizing this paradigm by using algorithms to determine which fashion items are likely to match from a human’s point of view. The demo as you'll see in Part 2 of this video, is built using their Custom Collections API. The API works on the concept of Transfer Learning which allows deep nets trained on one task, to be tweaked to work for other tasks using about 100x data than starting from scratch.

Deep Learning TV on

Indico Links

Credits
Nickey Pickorita (YouTube art) -
Isabel Descutner (Voice) -
Dan Partynski (Copy Editing) -
Marek Scibior (Prezi creator, Illustrator) -
Jagannath Rajagopal (Creator, Producer and Director) -

[DeepLearningTV]

This project is a collaboration with indico! First clip of 2 on Fashion Matching - this one explains transfer learning. Part 2 - the demo will come out Thursday.

[yuliiahetman]

Where can I find the code of this algorithm/model?

[DeepLearningTV]

Hey all - check out the fashion matching tutorial as promised!

[ybenzaki]

Hey, that is a really helpful video !

I have just on question not related to the topic of the video... How do
you make these videos ? is there some sort of software to have such high
quality animations ?

Thank you

[flydragoon]

able to share slides in the series. It's really helpful. Thanks

[guillaumedemonet]

Really smart company indeed, thanks for these enlightening series. Just to give a bit more depth to a potential reader, the techniques implied here are called fine-tuning, which is a really popular and efficient approach for vision tasks and heavy models. A good reminder also that its parent field of research, transfer learning, has still much to explore. Recent papers on that matter are frequent, showing new and impressive results -- for the curious (brave) reader, I suggest you try out arxiv-sanity.com to get a peek at state of the art results.