Encoder Decoder Network - Computerphile

Papers included in this Computerphile:

This video was filmed and edited by Sean Riley.

[normalnews]

I would love a Mike Pound playlist. Or at least I would have if I hadn't already watched all the videos with him.

[minihjalte]

Great animation work on this episode Sean.

[devontebroncas]

Im writing a proposal reviewing CodeT5 neural architecture and am so confused about encoder-decoder technique mentioned there.

Super stoked to see a Computerphile video on it!

[tenseikenzx-]

Another awesome lecture by Dr Mike Pound :D. Dang I wish you were my ML/AI lecturer back when I was learning this stuff.

[hart]

You can feel the passion when he speaks until nearly out of breath

[kevon]

Love this channel. Every concept is so intuitively explained.

[undefBehav]

great talk. if Mike could discuss the model interpretability in deep learning models for the next one, that would make my day!

[micahgilbertcubing]

I love the increasing collection of twisty puzzles on the shelf in the background

[SuperKnallex]

lol, dat face at 5:08 when he wanted to mention the use for military reasons :D

[ShubhamPatil-eevt]

Whoa! What an amazing explanation to such complex topic! Loved the articulation!!

[__someone__]

This is the best explanation about U-net I've ever seen.

[xyZenTV]

You guys remembered to make this video! Nice!

[rsage_]

It seems like a way to distill an image of identifiable objects in their most basic forms and then using that information to once again layer the identified objects onto less compressed versions of the image. An analog reverse to this might be to have a completed puzzle of an image where you'd identify a few key objects and tag them on a few pieces, then you'd take the puzzle apart and hold on to the key objects and place them in their respective locations on the table. From there, you can start to place the surrounding pieces around each key piece until it's once again understandable.

[rgbplaza]

Plant science sounds rad! Also, two Mike Pound videos in one week, I'd rather this type of pound than to win the national lottery!

[nullnull]

you are the best, I can't find this content out of this awesome channel

[vtrandal]

Downsampling by choosing the best of them? The max of them? No. First, the image must be low-pass filtered then simply downsample by discarding pixels. But then I see that you really do want to take the max when downsampling. Very interesting. Your GAN analogy at the end is excellent: the interior is like a generator and the higher resolution layers are like a discriminator.

[jeffsnox]

So basically the down up down sampling is doing what two separate systems working collaboratively could do - one to physically locate the item of interest and another to work on it? I'm working on speech recognition from 'images' generated using fast fourier - part of the solution involves locating the part of the image that contains the relevant information before inputting that into the recognition neural net - why would the procedure outlined in the video outperform two independent processes?

[vadrif-draco]

The GAN relation at the end was pretty helpful

[Jackisaboss]

That’s an awesome explanation. Thanks!

[BorisZandona]

Teaching is an art. Thank you so much for this video!