One can see the immediate applicablity in gaming. With improved source-output resolution, even motion pictures could minimize real-world shots for this approach... saves time and money, and increase safety by not having to close streets in the real world for filming. Exciting stuff.
I'm genuinely excited about computational holography, but I don't understand 80% of this video. I wish you could explain things in simpler terms for youtube.
i wonder why nobody even attempted to ever use this commercially... it's the only solution that is simultaneously solid-state and doesn't seem to sacrifice resolution. I've heard from a live presentation that generating the 2 plane images was supposedly very computationally heavy for them, but I bet it could be optimized, i.e. by using the z-buffer for depth data instead of rendering multiple view points.
yeah i was wondering why people weren't using sin's and cosine's cause i watched a video and the guy explained that, a neural network of L number of layers, and N number of nodes per Layer, which use relu activation, can perfectly match a function with N to the power L number of bends or turning points in its curve (assuming the neural network has a single scalar node output), i guess that is why it failed on the audio, there is a lot of turning point in audio data, so technical the SIREN networks performance can be matched by a large enough relu neural network, so am looking at SIREN as an optimization on the usual relu networks. Am glad i saw this, i will look into it further. i suspect that sinusoidal activation will be useful in domains with some sort of repetition, cause relu act more like threshold switches.
The music part was outstanding. Audio waveforms are just stacked sinewaves, as opposed to images or text where the input may not be too related to the sine function. So it just feels right to use sine activations and the required tweaks to make that work, instead of ReLUs, but I'm going to be careful with this as even though I have some experience in ML i haven't ever touched anything other than ReLUs, sigmoids, tanh and straight up linear activations
@@Oktokolo let me rephrase that then. Audio waveforms can be approximated by a relatively SMALL number of stacked sine waves, so it feels natural to use them in NNs. Everything can be approximated by infinite numbers of sine waves, but sometimes it doesn't make sense to do it
@@TileBitan It obviously makes sense for images as that is how the best compression algorithms use. It should also be possible to encode text reasonably well - even though the resulting set of weights is probably larger than the text itself when not encoding input of a huge language model...
@@Oktokolo i don't understand. Sounds are different amplitude waves with different frequencies inside the hearing range. Images nowadays can be 100M pixels with 3 times 256 on the BEST case scenario, where relationships between pixels can be really close to nothing. The case is completely different. The text case doesn't really have much to do with a wave. They might use FFTs for images but you gotta agree with me, for the same error you need way way less terms for sound than images.
@@TileBitan Doesn't matter whether it looks like it has anything to do with a wave or not or whether adjacent values look like they are in any relation to eachother. Treating data as signals and then encoding the signal as stacked waves just works surprisingly well. It might not work well for truly random bit noise. But most data interesting to humans seems to exhibit a surprisingly low entropy and can be compressed using stacked sines.
ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-izE7j1b95uI.html I got the idea yesterday to move the cursor in computer by use of this technology(for handicaps). I am sad because this invention was already invented 😔.Will you help me in doing this project to me please. Share the software you used sense the eyeball and I will make it. I think you will help me, thank you.
I got the idea yesterday to move the cursor in computer use of this technology(for handicaps). I am sad because this invention was already invented 😔.Will you help me in doing this project to me please. Share the software you used and I will make it. I think you will help me, thank you.
I got here by googling eyeball parallax because I noticed this effect in real life and wanted to see whether people actually thought about simulating it in the VR world. Apparently you guys did ^^
Hi, we saw your video, liked it and subscribed to Your channel. We are also fascinated by the 3D-VIEW-MASTER and the Stereography. We read the old View-Master Booklets on our Channel to the reels...come and see us :-)
so, you could bounce a laser beam off of the moon and tell the speed at which it's moving away or closer, assuming you had a detector that can sense the reflected light
Very nice work especially the sinusoidal activation. I like to point out Candes in 1997 covered it rigorously in "Harmonic Analysis of Neural Networks" about periodic activation function - "admissible neural activation function". Strangely enough, the paper is not even cited by the authors.