Discover and read the best of Twitter Threads about #NN

Most recents (6)

👾🧵 AI 101🧵 👾

Dzisiaj podstawy, czyli CO JEST CZYM w świecie #AI? 🤔

Czy sztuczna inteligencja i uczenie maszynowe to synonimy? Czy uczenie głębokie to sieć neuronowa? Gdzie na mapie umiejscowić #ChatGPT?

1/7 👇 Image
TL;DR: #AI#ML#NN#DL

Będzie bardzo krótko.

2/7 👇
SZTUCZNA INTELIGENCJA (AI, SI)

Nauka, która symuluje wykonywanie przez maszyny czynności zarezerwowanych dla ludzi i wymagających inteligencji.

To pojęcie jest najbardziej ogólne. Jak bardzo i jakie ma to konsekwencje? Zapraszam do lektury wczorajszej, przydługiej🧵 😉

3/7 👇
Read 8 tweets
Let's talk about NEURAL NETWORKS. 🧠

Most of you are probably familiar with them. 🧑‍💻

But not many know HOW they actually work and—even more importantly—WHY they work. 🔧

So, let's take a journey to understand what makes Neural Networks so effective... 📊

#ML #AI #NN

🧵👇
Let's start with a simple question...

❓ What problem are NNs trying to solve? 🤔

Generally speaking, NNs are trained on examples, to produce predictions based on some input values.

The example data (input + desired output) draws a curve that the NN is trying to fit.
In a nutshell, NNs are—like most ML tools—a fancy way to fit the curves inherently generated by the examples used to train it.

The more inputs it needs, and the more outputs it produces, the higher the dimension of the curve.

The simplest curve we can fit is ...a line! 😅
Read 21 tweets
If you are using matplotlib in your day to day coding activity and didn't no the crux of it, I want to you take a look at this below thread. I'm sure you will learn and apply it.

So, here is what all we need to know about matplotlib, an excellent visualization library in python
1. In this thread we will go through some basic patterns and practises to help you get started with the library

It will basically help us plot the data into the figures and can contain axes, i.e. an area where points can be specified in x/y/z co-ordinates

First let's import it Importing the library
2. The simple way of creating axes is using pyplot.subplots and we can Axes.plot to draw some data on the axes.

Below is how we can do it. using pyplot.subplotsOutput of the subplots
Read 21 tweets
Throwback to that time some dude said Arogya Setu will prevent Corona and now we're at 1million+ cases and someone tell me how good did Arogya Setu do for you!!!

#NN
Also... all that blood of reporting spent on reporting on this bogus-ness!!!
Someone/NITI Aayog, send me a report on the "effectiveness of Arogya Setu", wontcha?!???
Read 3 tweets
A "worrying analysis":

"18 [#deeplearning] algorithms ... presented at top-level research conferences ... Only 7 of them could be reproduced w/ reasonable effort ... 6 of them can often be outperformed w/ comparably simple heuristic methods."

Paper:
lnkd.in/dTaGCTv

#AI
[Updates worth tweeting]

2/
There is much concern about #reproducibility issues and flawed scientific practices in the #ML community in particular & #academia in general.

Both the issues and the concerns are not new.

Isn't it time to put an end to them?
3/
There are several works that have exposed these and similar problems along the years.

👏👏 again to @Maurizio_fd et al. for sharing their paper and addressing #DL algorithms for recommended systems (1st tweet from this thread).

But there is more, unfortunately:
Read 18 tweets
Image
§3.331
Any solution to the Kantian matrixial dialectic needs to not only enumerate or materialize possible solutions, but the halting condition for the problem rests on the liquidity (deparametrization) of the problem space.

#cryptocurrent #cryptocene #nickland Image
§3.332
Modernity provides a natural acceleration toward the solution, and we highlight only a horizon marking the entrance and exit boundary condition that would qualify as a true escape from it. This natural historical progression can be considered thermodynamic.
#cryptocurrent Image
Read 12 tweets

Related hashtags

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 ($3.00/month or $30.00/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 Become our Patreon

Thank you for your support!