MIT 6.S191 (2023): The Modern Era of Statistics

Рет қаралды 83,620

Күн бұрын

Пікірлер: 34

@JustAGuySurfingTheNet3393 Жыл бұрын

This presentation was a delight to watch! The ability of NCP architecture to learn causal relationships and focus on what's important is impressive!

@prithvishah2618 Жыл бұрын

As always, thank you very much :)

@ajaytaneja111 Жыл бұрын

What a great lecture... Beautiful!

@antonkot6250 Жыл бұрын

This approach to NN looks very promising to me. Wish the best luck to Dr. Hasani and his colleges

@Phliee Жыл бұрын

This is a truly great lecture!

@JoaoVitorBRgomes Жыл бұрын

I found interesting the concepts of double descent, kolmogorov functions, robustness and effective dimensionality (I think this is why dimensionality reduction techniques can be beneficial)

@aninvisibleneophyte Жыл бұрын

great lecture. thank you for sharing!!!! a gem on the horizon for all of us studying epistemology and ontology.

@mojganmadadi6242 Жыл бұрын

Hi, thanks for the great videos. Quick question, How do you visualize the activated neurons as in 41:09 in this video. could you please share is there is any package or software to do so? Thanks a bunch! Really enjoyed your lectures.

@superman39756 Жыл бұрын

This course has helped me learn so much! Thank you! This lecture was amazing especially!

@liu973 Жыл бұрын

The talk was fantastic, much like the other sessions in the series! I'd pinpoint this lecture as the point where I begin to sense a challenge in keeping pace. My takeaway was a general sense that LTC is leaning towards a more innovative strategy for enhancement rather than focusing solely on scaling and fine-tuning.

@tantzer6113 Жыл бұрын

So, 19 neurons as opposed to a much larger number of neurons. But is the amount of computation genuinely reduced? These liquid neurons seem much more complex; so, are there really savings in complexity/computation?

@khileshwarprasad9474 Жыл бұрын

Yes, Quantisation is the term.

@pavalep Жыл бұрын

Super Interesting Lecture 👍

@Adsgjdkcis 10 ай бұрын

This guy starts by saying ML isn't an ad-hoc field but by halfway through is introducing another ad-hoc architecture 🤣

@saharbehroozinia9700 Жыл бұрын

Very beautiful!

@santiagoblas8214 Жыл бұрын

Thank you!! This is gold

@abduljawad8689 Жыл бұрын

Great lecture

@eddiejennings5262 Жыл бұрын

Thank you! Great lecture. Very respectfully, I've thought about dynamical systems and neural networks, but not specifically with over parametrization, biologically inspired liquid networks and dynamic causal models. Great examples of learning causal relationships.

@venkatasivagabbita788 Жыл бұрын

It is not that n equations require n unknowns - it is that solving for n unknowns requires n equations. Why would equations require unknowns?

@sheevys 8 ай бұрын

Interesting view regarding the kolomogorov Arnold representation. His buddies at MIT just released KAN paper, I wonder how this idea evolves.

@peki_ooooooo Жыл бұрын

Yeah, we need to explore new architecture for neuron networks. Nowadays architecture mainly depends on backprop( one way to learn), this method is not right. Learning from the forward pass and from the result(backward pass) should be two main factors of the learning process.

@RajabNatshah Жыл бұрын

Thank you :)

@liujay1670 Жыл бұрын

hmm. I've thought about the reason for that for a while and my conclusion is that this "double descent" occurs when using CNNs to image data where the convolution produces more number of samples than that of the original set (with some redundancy).