Discover and read the best of Twitter Threads about #dl

Most recents (21)

👾🧵 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

Będzie bardzo krótko.

2/7 👇

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
In a highly anticipated move, @Google yesterday announced that they are launching Bard, a conversational AI app that is based on their LaMDA model.

LaMDA - Language Model for Dialogue Applications - has been around for at least a year, but due to variety of considerations it has never been accessible to to the public.

Bard will be using a lighter, more computationally efficient, version of LaMDA. Bard’s rollout will proceed gradually, and in a month or so Google will be releasing an API for it to some trusted partners and developers.

Read 5 tweets
Deep Learning and Neural Networks have become the default approaches to Machine Learning in recent years. However, despite their spectacular success in certain domains (vision and NLP in particular),

their use across the board for all ML problems and with all datasets is problematic, to say the least. Oftentimes better and more robust results can be obtained with simpler, easier to train and deploy, classical ML algorithms.

One such “traditional” approach was recently used to reevaluate sleep scoring on a few publicly available datasets. The results were published in the journal of Biomedical Signal Processing and Control.

Read 5 tweets
Last week @DeepMind’s research on AlphaCode - a competative programming system - has been published in Science. AlphaCode has been able to beat 54% of humans on a competative coding challenges, putting it on par with many junior-level developers.

The original announcement from DeepMind came out in February, which in the fast-paced world of AI is already ancient history.

The explosive rise of generative AI over the past few months will most certainly have a major impact, if it already hasn’t, on the future versions of AlphaCode and similar AI-enabled coding resources.

Read 4 tweets
Last week @OpenAI released ChatGPT - a Large Language AI Model that interacts with users in a natural conversational way. The chatbot is able to answer complex questions, even in highly technically demanding categories.

It is also able to answer the follow up question, backtrack on wrong assumptions, and provide other detailed resources, including code fragments.

Most people in tech consider this to be the greatest technological advancement of the year. Many of us consider it even more epochal, perhaps one of the biggest turning points in history.

Read 7 tweets
PyTorch 2.0 is out! This major release upgrade brings about many new features, but the main improvements are under the hood.

1/6 Image
The three main principles behind PyTorch

1. High-Performance eager execution
2. Pythonic internals
3. Good abstractions for Distributed, Autodiff, Data loading, Accelerators, etc.

PyTorch 2.0 is fully backward compatible with the previous versions of PyTorch.

The main new feature is torch.compile, "a feature that pushes PyTorch performance to new heights and starts the move for parts of PyTorch from C++ back into Python."

Read 6 tweets
This week @NVIDIA open sourced the 3D object generation AI model, GET3D. GET3D is a generative model of high quality 3D textured shapes learned from images.

Trained using only 2D images, GET3D generates 3D shapes with high-fidelity textures and complex geometric details.

These 3D objects are created in the same format used by popular graphics software applications, allowing users to immediately import their shapes into 3D renderers and game engines for further editing.

Read 4 tweets
A very good paper I came across this morning by the @DeepMind researchers. For the past five years Transformers have been one of the most dominant approaches to Deep Learning problems, especially in the #NLP domain.

However, despite many interesting papers on the topic, and lots of good open code, there has been a noticeable lack of *formal* definition of what transformed are, especially on the level of pseudocode.

This paper aims to rectify that. It provides pseudocode for almost all major Transformer architectures, including training algorithms.

Read 5 tweets
#Highlights2021 for me: our #survey on efficient processing of #sparse and compressed tensors of #ML/#DNN models on #hardware accelerators published in @ProceedingsIEEE.
RT/sharing appreciated. 🧵
Context: Tensors of ML/DNN are compressed by leveraging #sparsity, #quantization, shape reduction. We summarize several such sources of sparsity & compression (§3). Sparsity is induced in structure while pruning & it is unstructured inherently for various applications or sources. Various sources induce stru...Common structures of sparsi...
Likewise, leveraging value similarity or approximate operations could yield irregularity in processing. Also, techniques for size-reduction make tensors asymmetric-shaped. Hence, special mechanisms can be required for efficient processing of sparse and irregular computations.
Read 12 tweets
#SC21: @HPC_Hyperion #HPC Market briefing (without the breakfast this time 😉 )

Despite Covid, #Fugaku single-handedly saved the HPC revenue numbers for 2020 - a billion dollars makes a difference!
@HPC_Hyperion .@HPE is the top #HPC vendor, followed by @DellTech

@Fujitsu_Global jumped due #3 due to #Fugaku - so this is their 15 minutes of fame :-)

@InspurServer & @lenovo make up the Top 5

@HPC_Hyperion The broader on-prem #HPC market

#HPC #storage remains #2 after compute, which is the biggest item as usual

Read 28 tweets
@amaarora really explained #convolutions very well in #fastbook week 12 session which can be viewed here

I wasn't able to write a blog post explaining my learnings from the stream but would threfore write a 🧵

After going through 1st part of #convolutions chapter, have cleared a concept and was introduced to two new concepts.

1. How depthwise convolutions work (3/n)
2. Dilated convolutions (7/n)
3. Alternate interpretation of #stride (9/n)

When we have a n-channel input and a m-channel output, we need to convolve over not only 2-Dimensions (W x H) but also across the depth D.

An RGB image for example has 3 channels

Let us consider we want to derive 10 feature maps from this input.
Read 10 tweets
Read 259 tweets
Read 284 tweets
Me hace muchísima ilusión presentaros el curso de verano que organizamos @andortizg y un servidor para @UNIAuniversidad:

Introducción práctica a la Inteligencia Artificial y el Deep Learning.

Procedo a vender la moto :)
Inteligencia Artificial… Redes Neuronales…


Dos campos permean las ciencias en el siglo XXI: la #estadística y la #computación. Combinados, dan lugar al Aprendizaje Automático, el Machine Learning. O como hacer que las máquinas "aprendan"
Como cuento en los monólogos, las máquinas más bien nos quitan "trabajo".

El Machine Learning es herramienta fundamental para automatizar procesos, y hoy en día no se puede entender sin las redes neuronales (la base del Deep Learning #DL).
Read 20 tweets
Ho appena sentito @renatobrunetta al #TG5 e schiumavo alla bocca dopo un pomeriggio passato a caricare dati inutili richiesti da una organizzazione che li ha già. (/) @DonChisciotte_P @liberioltre @LorenaLVilla
Dopo, dovrò continuare la mia settimana con adempimenti senza senso. E lui vuole "assumere i giovani migliori" (/)
Forse, e dico forse, potrebbero cominciare dal fare un paio di modifiche. Una, scrivere un bel #DL che renda non punibile il cittadino che ignori qualunque richiesta di dati già in possesso della #PA (/)
Read 4 tweets
A deeply interesting tutorial by @fchollet @MelMitchell1 @ChrSzegedy at #NeurIPS2020

"#Abstraction & #Reasoning in #AI systems: Modern Perspectives "

or "What are abstraction, generalization and analogic reasoning?"

@fchollet begins by laying some foundations in notation and background.

E.g., Generalization is a spectrum (and we are looking at lower bands in #ML nowadays)

And Abstraction? It is the engine behind generalization!

And of course it comes in different flavors:

- program-centric: that is akin to high-level reasoning (inducing & merging programs)

- value-centric (interpolating examples) 👈 essentially what #DL does and excels at!

Read 15 tweets
I've been witnessing the "battles" both around advancements in #AI and of the #AI silos since I entered into the field more than 30 years ago.

It has never been so sick and flawed as in the #DeepLearning and GPT-3 era.
The intensity of the #AI battles varies depending on many factors.

They can boil around concrete examples of algorithms.

They even can explode when some concrete people either second or criticize them. It's either white or black, it's difficult to find gray tones in between.
In what follows, I'll be adding some examples of what I've been observing in #AI discussions in recent years 👇
Read 20 tweets
Excited to introduce #3DRCAN for denoising, super resolution and expansion microscopy. Super proud of this colab with Hari Shroff, Jiji Chen et al.

@NIBIBgov @arpcomplex



#microscopy #aimicroscopy #aivia

"Three-dimensional residual channel attention networks denoise and sharpen fluorescence microscopy image volumes"

J Chen, H Sasaki, H Lai, Y Su, J Liu, Y Wu, A Zhovmer, C Combs, I Rey-Suarez, H Chang, C Huang, X Li, M Guo, S Nizambad, A Upadhyaya, J Lee, L Lucas, H Shroff.
We are particularly interested in characterizing the limits of #deeplearning based approaches to image restoration. You will find several experiments comparing several best-in-class approaches: #3DRCAN, #CARE, #SRResNet and #ESRGAN.

#microscopy #aimicroscopy #iSIM

Read 17 tweets
Remember Dutch artist Bas Uterwijk who used #DL to create realistic-looking images of famous people like Napoleon Bonaparte, Vincent Van Gogh, and others
Went to created few collages with original image and AI generated one
Thread 👇🏻
David by Michelangelo (1/x) not bad huh 😻
Nicola Machiavelli (2/x)
Read 12 tweets
DAY 1: Python Installation on Windows.

Let start our 30 days journey of Twitter Python Training with:
* How to Install Python.
*Likely issues to faced after the installation of Python.

#TwitterPython #Python #ML #DL #AI #DataScience
I will like to talk about two ways of Installing and running Python on your personal computer and the method I 'prefer' out of the two.

1. Direct Installation from Python Website
2. Installation from Anaconda Website.

#TwitterPython #Python #ML #DL #AI #DataScience
1st Method:
Direct Installation from Python Website

Installing Python on your PC is not a difficult task.
It involves just a few simple steps:
a. Download binaries from
b. Install the binaries
c Add Python to system environment variables
d. Install pip
Read 9 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."


[Updates worth tweeting]

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?
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

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!