Discover and read the best of Twitter Threads about #dl

Most recents (15)

This week @Google researchers announced Minerva, an internally developed project that can answer mathematical questions and tackle other complex topics such as physics.

1/5 Image
This project makes some really impressive gains with automatic NLP approach to tackling the challenging quantitative reasoning problems. Minerva is a large language model pretrained on general natural language data and further trained on technical content.

The model achieves state-of-the-art performance on technical benchmarks without the use of external tools.

Read 5 tweets
Neural Network with Flax 🚀🚀🚀

#Flax is a Google #OpenSource Python library for neural network applications for JAX 🌈. While most folks are familiar with Google #TensorFlow and #Keras, 🧵 👇🏼

#DataScience #deeplearning #DL #python Image
While most folks are familiar with Google TensorFlow and Keras, Flax is less known, but it is mainly used by researchers and engineers at Google.

One of the core use cases of this library is for #NLP #Transformers and image recognition applications Image
Among the Flax applications, you can find:
✅ Neural network API (flax.linen): Dense, Conv, Norm, Attention, Pooling, Cell, Dropout
✅ Utilities and patterns: replicated training, serialization and checkpointing, metrics, prefetching on device
✅ Educational examples Image
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!