Kone ismael

102 posts

Kone ismael banner
Kone ismael

Kone ismael

@iskodeur

Katılım Temmuz 2012
45 Takip Edilen71 Takipçiler
Kone ismael retweetledi
Paul Azunre
Paul Azunre@pazunre·
Quick demo of the voice to voice translation between English and Twi that you can try today on our web app. This one is from the perspective of a tourist visiting Ghana and needing to get around. Brought to you by the amazing team at @GhanaNLP @algorineinc
English
52
674
1.4K
165.1K
Kone ismael retweetledi
Graham Neubig
Graham Neubig@gneubig·
I had to travel 26 hours and spend $2000+ to join #ICLR2023 in Rwanda. But people in Africa have to do this every time a conference is held in US. What happens when we make it easier to participate? 1530% higher registrations from Africa. This is important and must continue.
Graham Neubig tweet media
English
17
183
981
145.5K
Kone ismael retweetledi
Anthropic
Anthropic@AnthropicAI·
We’ve trained language models to be better at responding to adversarial questions, without becoming obtuse and saying very little. We do this by conditioning them with a simple set of behavioral principles via a technique called Constitutional AI: anthropic.com/constitutional…
Anthropic tweet media
English
26
226
1.2K
866K
Kone ismael retweetledi
Ross Wightman
Ross Wightman@wightmanr·
Within a day, timm will be past the 20k mark in GitHub stars. It's been quite the journey getting here. Thanks to support of community, incl users and contributers that helped out with models, bug fixes, reports, helping other users. github.com/rwightman/pyto…
Ross Wightman tweet media
English
4
35
311
0
Kone ismael retweetledi
Asiedu Brempong
Asiedu Brempong@asiedubrempong·
Announcing decoder denoising pretraining for semantic segmentation: arxiv.org/abs/2205.11423 Take a U-Net, pretrain the encoder on classification, pretrain the decoder on denoising, and fine-tune on semantic segmentation. This achieves a new SoTA on label efficient segmentation.
GIF
English
16
111
631
0
Kone ismael retweetledi
Dr. Jochen Papenbrock
Dr. Jochen Papenbrock@JoPapenbrock·
NVIDIA Deep Learning Institute has launched a new free self-paced course, Disaster Risk Monitoring Using Satellite Imagery. Learn how to build and deploy a deep learning model to automate the detection of flood events using satellite imagery. Enroll now! bit.ly/3u3S8m9
English
0
48
189
0
Kone ismael retweetledi
Jeremy Howard
Jeremy Howard@jeremyphoward·
2022 will mark the return for the @fastdotai course of neural nets implemented in spreadsheets!
Jeremy Howard tweet media
English
8
34
335
0
Kone ismael retweetledi
Jeremy Howard
Jeremy Howard@jeremyphoward·
I am over the moon to announce: 1) I'm now a professor at University of Queensland (UQ), the top institute in my home state! 2) I'll be teaching a brand new deep learning course at UQ from April, which will form the basis of a new @fastdotai course! 🧵 eait.uq.edu.au/article/2022/0…
English
128
172
2.6K
0
Kone ismael retweetledi
Helen Miles
Helen Miles@HappyFamilyDoc·
I don’t understand why this isn’t being reported more widely.
Helen Miles tweet media
English
221
3K
5.8K
0
Kone ismael retweetledi
merve
merve@mervenoyann·
For my midterm I read almost all of the Deep Learning book, until my finals (in two months) I'm writing a very comprehensive blog post that contains my notes and the TF Keras code for each architecture, how (ELI5 maths) and why they work, where to use which 🤓
merve tweet media
English
34
200
1.7K
0
Kone ismael retweetledi
Lucas Nestler
Lucas Nestler@Clashluke·
I want to retract this tweet publicly: twitter.com/_clashluke/sta… It is incorrect and causes unnecessary harm to the authors of "PoolFormer: MetaFormer is Actually What You Need for Vision" (arxiv.org/abs/2111.11418). Using just AvgPool and MLP, they outperform most models. 1/6
Lucas Nestler tweet media
Lucas Nestler@Clashluke

@ChrSzegedy @ak92501 Unfortunately, the reason their model worked so well has nothing to do with architectural changes. Instead, they use heavy regularizations and SOTA modifications on their model but not on the baselines. If you account for that, they suddenly underperform a simple ResNet-RS.

English
2
22
224
0
Kone ismael retweetledi
Radek Osmulski
Radek Osmulski@radekosmulski·
What a cool project! Plus the code is available and there is a step by step walkthrough in the Jupyter NB 🤩 Not sure how it is possible, but the blog post is even better 😁 Model training is done with @fastdotai! What a treasure! Added to my reading list.
Jimmie Munyi@jimmie_munyi

I used Deep Learning to create a Real Time Sign Language Classifier that runs on the webcam. The whole project is done from scratch. You can find all the code in my github repo: github.com/jimmiemunyi/Si… Here is a blog post on the same topic: : jimmiemunyi.github.io/blog/ 😃😃

English
3
43
313
0
Kone ismael retweetledi
An ka taa
An ka taa@ankataa_project·
Updated version of the Intermediate Subscription is live! Video workbooks with vocab and interactive exercises for anyone ready to go beyond the basics in Bambara/Jula :-) ankataa.com/intermediate-s…
English
0
1
1
0
Kone ismael retweetledi
Ivan Yashchuk
Ivan Yashchuk@IvanYashchuk·
The new chapter in the Python array interoperability story. We (me and my colleagues at @quansightai together with the library maintainers) are planning to add GPU & distributed arrays support for SciPy, scikit-learn, and scikit-image. Find out more: labs.quansight.org/blog/2021/11/p…
English
3
39
146
0
abhishek
abhishek@abhi1thakur·
What is AI? Wrong answers only!
English
160
4
101
0
Kone ismael retweetledi
rapha
rapha@rapha_gl·
We all know NNs are super expressive, so why is it that models seem to make similar mistakes? In our new work, we investigate how training methodology⚙️ affects learned representations🧠 and prediction behavior🏃🏽‍♀️ 📄 arxiv.org/pdf/2110.12899… 🧵 Read on for the surprises we found!
English
6
74
344
0

Keşfet

@GhanaNLP @algorineinc @fastdotai @TheZachMueller @quansightai @sarahookr @abhi1thakur @elonmusk