How many parameters do you need in your neural network to solve any problem? πŸ€”

GPT-3 has 175 billion, MT-NLG has 530 billion and Wu Dao has 1.75 trillion.

But the truth is you only need 1 parameter. No, not 1 billion. Just a single parameter!

Let me explain πŸ‘‡
Yes, of course, I'm trolling you, but only a little bit 😁

I want to show you this very cool work by @ranlot75 about how to fit an arbitrary dataset with a single parameter and the following function

github.com/Ranlot/single-…

πŸ‘‡
@ranlot75 Here are examples of some 2D image datasets. You see the parameter alpha and the reconstructed image.

Now, let me give you some high-level intuition how this works πŸ‘‡
@ranlot75 There are infinitely many real numbers between 0 and 1. So, what we could do is create a number alpha like this:

alpha = 0.<dataset>...

<dataset> is just a series of numbers and we can encode our entire dataset in there! This is how the whole fish number looks like.

πŸ‘‡
@ranlot75 You need some clever math to encode everything into this format and to define a function that can recover the information back, but it is doable.

Check the full paper and the code on GitHub for details:
β–ͺ️ arxiv.org/abs/1904.12320
β–ͺ️ github.com/Ranlot/single-…

πŸ‘‡
@ranlot75 Now, does it generalize well? Of course not! πŸ˜„ This is the clearest case of overfitting there is...

Is it practical? Lol, no 🀣

Is it very cool? Yes!
@ranlot75 I'm posting similar threads on machine learning and web3 topics on a regular basis.

Follow me @haltakov for more!

β€’ β€’ β€’

Missing some Tweet in this thread? You can try to force a refresh
γ€€

Keep Current with haltakov.eth | (πŸ€–,🧠)

haltakov.eth | (πŸ€–,🧠) Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @haltakov

Jan 18,
The Internet is already decentralized, why do we need web3? πŸ€”

This is a common critique of web3. However, decentralization on its own is not always enough - sometimes we need to agree on a set of facts.

Blockchains give us a consensus mechanism for that!

Thread 🧡

1/12
The Internet is built of servers that communicate using open protocols like HTTP, SMTP, WebRTC etc. Everybody can set up a server and participate. It is decentralized!

However, if two servers distribute contradicting information, how do you know which one is right?

2/12
This is what blockchains give us, a way for decentralized parties to agree on one set of facts. They offer a consensus mechanism!

Imagine the blockchain as a global public database that anybody can read and nobody can falsify - every transaction/change needs to be signed.

3/12
Read 13 tweets
Jan 18,
How decentralized is web3 really?

While there is a lot of hype around web3, NFTs, and decentralized apps (dApps), there is also a lot of criticism. Today, I'll focus on the critique that web3 is actually too centralized.

Let's try to have an honest discussion πŸ‘‡
These are the main arguments I see regularly. Please add more in the comments.

1️⃣ The Internet is already decentralized
2️⃣ It is inefficient
3️⃣ Everything can be implemented better using a centralized approach
4️⃣ Important services are centralized

πŸ‘‡
I was inspired to write this in part after reading this great article by @moxie pointing some of the problems with the current state of web3. If you've been living under a rock in the last weeks, make sure you check it out:

moxie.org/2022/01/07/web…

πŸ‘‡
Read 9 tweets
Dec 29, 2021
You think you know what is an NFT? Well, think again...

You are doing it wrong if you think about NFTs as pixelated images of punks, toads, or apes. It is not about the JPEG!

A better mental model for thinking about NFTs πŸ‘‡
Forget the images for now. Owning an NFT means that your wallet address is listed as the owner of a specific digital asset on the blockchain.

Digital assets are organized in collections and an NFT is one specific piece of this collection.

Let's look at an example πŸ‘‡
I own an NFT from the @underfittedio membership collection - a membership card.

You can now check the collection on the blockchain and can see that my wallet address is the owner of token ID 4.

Everybody can check this. Nobody can change it - except me!

How is this useful? πŸ‘‡
Read 26 tweets
Dec 21, 2021
Things are getting more and more interesting for AI-generated images! 🎨

GLIDE is a new model by @OpenAI that can generate images guided by a text prompt. It is based on a diffusion model instead of the more widely used GAN models.

Some details πŸ‘‡
@OpenAI GLIDE also has the interesting ability to perform inpainting allowing for some interesting usages.

πŸ‘‡
@OpenAI Here is the full paper

arxiv.org/abs/2112.10741

πŸ‘‡
Read 5 tweets
Dec 17, 2021
How to evaluate your ML model? πŸ“

Your accuracy is 97%, so this is pretty good, right? Right? No! ❌

Just looking at the model accuracy is not enough. Let me tell you about some other metrics:
β–ͺ️ Recall
β–ͺ️ Precision
β–ͺ️ F1 score
β–ͺ️ Confusion matrix

Let's go πŸ‘‡

#RepostFriday
We'll use this example in the whole thread - classifying traffic light colors (e.g. for a self-driving car).

Yellow traffic lights appear much less often, so our dataset may look like this.

This means our model could reach 97% accuracy, by ignoring all 🟑 lights. Not good!

πŸ‘‡
Let's assume now that we trained our model and we get the following predictions.

Do you think this model is good? How can we quantitatively evaluate its performance? How should it be improved?

Let's first discuss the possible error types πŸ‘‡
Read 12 tweets
Dec 15, 2021
First officially approved Level 3 self-driving system in Germany.

This is significant because it is the first time an autonomous system that takes the *driving responsibility* from the driver is approved for mass production!

europe.autonews.com/automakers/mer…

πŸ‘‡
The main difference between Level 2 and Level 3 systems is that self-driving systems become legally responsible for the actions of the cars when in autonomous mode!

All driver assist systems on the market now (including Tesla) are Level 2 systems.



πŸ‘‡
While Waymo and Cruise have Level 4 systems running as a beta in some cities, there are different challenges putting this tech in consumer vehicles and in cars that don't have a huge sensor rack costing tens of thousands of dollars on the roof.

πŸ‘‡
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(