Forwarded from Towards NLP🇺🇦
Models based on graphs are quite important for a lot of tasks in NLP. There is an overview from Michael Bronstein about what he is expecting for upcoming year for the Graph ML field:
1. Geometry becomes increasingly important in ML.
2. Message passing is still the dominant paradigm in GNNs.
3. Differential equations give rise to new GNN architectures.
4. Old ideas from Signal Processing, Neuroscience, and Physics get a new life.
5. Modeling complex systems requires going beyond graphs.
6. Reasoning, axiomatisation, and generalisation are still big open questions in Graph ML.
7. Graphs become increasingly popular in Reinforcement Learning, but probably still have a way to go.
8. AlphaFold 2 is a triumph of Geometric ML and a paradigm shift in structural biology.
9. Drug discovery and design benefits from GNNs and their confluence with Transformers.
10. AI-first drug discovery is increasingly using Geometric and Graph ML.
11. Quantum ML benefits from graph-based methods.
[link]
1. Geometry becomes increasingly important in ML.
2. Message passing is still the dominant paradigm in GNNs.
3. Differential equations give rise to new GNN architectures.
4. Old ideas from Signal Processing, Neuroscience, and Physics get a new life.
5. Modeling complex systems requires going beyond graphs.
6. Reasoning, axiomatisation, and generalisation are still big open questions in Graph ML.
7. Graphs become increasingly popular in Reinforcement Learning, but probably still have a way to go.
8. AlphaFold 2 is a triumph of Geometric ML and a paradigm shift in structural biology.
9. Drug discovery and design benefits from GNNs and their confluence with Transformers.
10. AI-first drug discovery is increasingly using Geometric and Graph ML.
11. Quantum ML benefits from graph-based methods.
[link]
👍36❤4
Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study
Some time ago in a different world one of the channel editors shared permmission to use data from sleep & activity tracker Oura Ring to develop an algorithm for COVID-19 prediction.
Results of this study continue to arrive. Today team shared the second manuscript from the first TemPredict Study in Nature Scientific Reports. This manuscript details an algorithm designed to detect COVID-19 using data from the Oura Ring. Alogirthm publication: www.nature.com/articles/s41598-022-07314-0
The first publication from the first TemPredict Study will continue to be available online for you to access at any time, at this link: https://www.nature.com/articles/s41598-020-78355-6
The first publication from the second TemPredict Study (correlations between data from the Oura Ring and data from a LabCorp antibody blood test) will also continue to be available online for you to access at any time, at this link: https://www.mdpi.com/2076-393X/10/2/264
That's the power of the international collaboration 💪
#oura #covid #biolearning #medical #health
Some time ago in a different world one of the channel editors shared permmission to use data from sleep & activity tracker Oura Ring to develop an algorithm for COVID-19 prediction.
Results of this study continue to arrive. Today team shared the second manuscript from the first TemPredict Study in Nature Scientific Reports. This manuscript details an algorithm designed to detect COVID-19 using data from the Oura Ring. Alogirthm publication: www.nature.com/articles/s41598-022-07314-0
The first publication from the first TemPredict Study will continue to be available online for you to access at any time, at this link: https://www.nature.com/articles/s41598-020-78355-6
The first publication from the second TemPredict Study (correlations between data from the Oura Ring and data from a LabCorp antibody blood test) will also continue to be available online for you to access at any time, at this link: https://www.mdpi.com/2076-393X/10/2/264
That's the power of the international collaboration 💪
#oura #covid #biolearning #medical #health
Nature
Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study
Scientific Reports - Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study
👍14
Forwarded from Machinelearning
🗿 StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
Github: https://github.com/facebookresearch/StyleNeRF
Video: https://jiataogu.me/style_nerf
Paper: https://arxiv.org/abs/2110.08985
Project: https://jiataogu.me/style_nerf/
Dataset: https://github.com/facebookresearch/StyleNeRF#dataset
@ai_machinelearning_big_data
Github: https://github.com/facebookresearch/StyleNeRF
Video: https://jiataogu.me/style_nerf
Paper: https://arxiv.org/abs/2110.08985
Project: https://jiataogu.me/style_nerf/
Dataset: https://github.com/facebookresearch/StyleNeRF#dataset
@ai_machinelearning_big_data
👍23❤7💩1
Deep Neural Nets: 33 years ago and 33 years from now
Great post by Andrej Karpathy on the progress #CV made in 33 years.
Author's ideas on what would a time traveler from 2055 think about the performance of current networks:
* 2055 neural nets are basically the same as 2022 neural nets on the macro level, except bigger.
* Our datasets and models today look like a joke. Both are somewhere around 10,000,000X larger.
* One can train 2022 state of the art models in ~1 minute by training naively on their personal computing device as a weekend fun project.
* Today’s models are not optimally formulated, and just changing some of the details of the model, loss function, augmentation or the optimizer we can about halve the error.
* Our datasets are too small, and modest gains would come from scaling up the dataset alone.
* Further gains are actually not possible without expanding the computing infrastructure and investing into some R&D on effectively training models on that scale.
Website: https://karpathy.github.io/2022/03/14/lecun1989/
OG Paper link: https://yann.lecun.com/exdb/publis/pdf/lecun-89e.pdf
#karpathy #archeology #cv #nn
Great post by Andrej Karpathy on the progress #CV made in 33 years.
Author's ideas on what would a time traveler from 2055 think about the performance of current networks:
* 2055 neural nets are basically the same as 2022 neural nets on the macro level, except bigger.
* Our datasets and models today look like a joke. Both are somewhere around 10,000,000X larger.
* One can train 2022 state of the art models in ~1 minute by training naively on their personal computing device as a weekend fun project.
* Today’s models are not optimally formulated, and just changing some of the details of the model, loss function, augmentation or the optimizer we can about halve the error.
* Our datasets are too small, and modest gains would come from scaling up the dataset alone.
* Further gains are actually not possible without expanding the computing infrastructure and investing into some R&D on effectively training models on that scale.
Website: https://karpathy.github.io/2022/03/14/lecun1989/
OG Paper link: https://yann.lecun.com/exdb/publis/pdf/lecun-89e.pdf
#karpathy #archeology #cv #nn
karpathy.github.io
Deep Neural Nets: 33 years ago and 33 years from now
Musings of a Computer Scientist.
👍48😢4🤮3🥰2😁2❤1
Forwarded from Machinelearning
💭 NeuralSpeech is a research project in focusing on neural network based speech processing
Github: https://github.com/microsoft/NeuralSpeech
Paper: https://arxiv.org/pdf/2109.14420v3.pdf
Speech Research: https://speechresearch.github.io/
Dataset: https://paperswithcode.com/dataset/aishell-1
@ai_machinelearning_big_data
Github: https://github.com/microsoft/NeuralSpeech
Paper: https://arxiv.org/pdf/2109.14420v3.pdf
Speech Research: https://speechresearch.github.io/
Dataset: https://paperswithcode.com/dataset/aishell-1
@ai_machinelearning_big_data
❤9👍7
Forwarded from Artificial Intelligence
🦾 Global Tracking Transformers
Github: https://github.com/xingyizhou/GTR
Demo: https://github.com/facebookresearch/detectron2/blob/main/GETTING_STARTED.md
Paper: https://arxiv.org/abs/2203.13250v1
Dataset: https://paperswithcode.com/dataset/mot17
https://t.iss.one/ArtificialIntelligencedl
Github: https://github.com/xingyizhou/GTR
Demo: https://github.com/facebookresearch/detectron2/blob/main/GETTING_STARTED.md
Paper: https://arxiv.org/abs/2203.13250v1
Dataset: https://paperswithcode.com/dataset/mot17
https://t.iss.one/ArtificialIntelligencedl
❤18👍12
Forwarded from Artificial Intelligence
🔍 Exploiting Explainable Metrics for Augmented SGD
A new explainability metrics that measure the redundant information in a network's layers and exploit this information to augment the Stochastic Gradient Descent
Project
Code: https://github.com/mahdihosseini/rmsgd
Paper: https://arxiv.org/pdf/2203.16723v1.pdf
Dataset: https://paperswithcode.com/dataset/mhist
@ArtificialIntelligencedl
A new explainability metrics that measure the redundant information in a network's layers and exploit this information to augment the Stochastic Gradient Descent
Project
Code: https://github.com/mahdihosseini/rmsgd
Paper: https://arxiv.org/pdf/2203.16723v1.pdf
Dataset: https://paperswithcode.com/dataset/mhist
@ArtificialIntelligencedl
👍28❤1
Big step after first DALL·E — DALL·E 2
In January 2021, OpenAI introduced DALL·E. One year later, their newest system, DALL·E 2, generates more realistic and accurate images with 4x greater resolution.
The first DALL·E is a transformer model. It receives both the text and the image as a single stream of data containing up to 1280 tokens, and is trained using maximum likelihood to generate all of the tokens, one after another. This training procedure allows DALL·E to not only generate an image from scratch, but also to regenerate any rectangular region of an existing image that extends to the bottom-right corner, in a way that is consistent with the text prompt.
In the second DALL·E they reformated method and now it is CLIP + diffusion model.
CLIP to encode text prior and diffusion model to decode resulting embeding to high resolution image.
So it’s simply GLIDE, but with some tweaks. To generate high resolution images, they train two diffusion upsampler models.
But the results are amazing. Despite that it is cherry picks of course :))
- paper
- blog with images and demos
- video
In January 2021, OpenAI introduced DALL·E. One year later, their newest system, DALL·E 2, generates more realistic and accurate images with 4x greater resolution.
The first DALL·E is a transformer model. It receives both the text and the image as a single stream of data containing up to 1280 tokens, and is trained using maximum likelihood to generate all of the tokens, one after another. This training procedure allows DALL·E to not only generate an image from scratch, but also to regenerate any rectangular region of an existing image that extends to the bottom-right corner, in a way that is consistent with the text prompt.
In the second DALL·E they reformated method and now it is CLIP + diffusion model.
CLIP to encode text prior and diffusion model to decode resulting embeding to high resolution image.
So it’s simply GLIDE, but with some tweaks. To generate high resolution images, they train two diffusion upsampler models.
But the results are amazing. Despite that it is cherry picks of course :))
- paper
- blog with images and demos
- video
🔥41👍16😁2🤔1
Forwarded from Silero News (Alexander)
Silero TTS V3 Finally Released
We have just released a brand new Russian speech synthesis model.
We have made a number of promises we kept:
- Model size reduced 2x;
- New models are 10x faster (!);
- We added flags to control stress;
- Now the models can make proper pauses;
- High quality voice added (and unlimited "random" voices);
- All speakers squeezed into the same model;
- Input length limitations lifted, now models can work with paragraphs of text;
- Pauses, speed and pitch can be controlled via SSML;
- Sampling rates of 8, 24 or 48 kHz are supported;
- Models are much more stable — they do not omit words anymore;
Next steps:
- Release models for the CIS languages, English, some European languages and Hindic languages
- Even further 2-4x speed up
- Updated stress model
- Phonemes support and and built-in voice transfer
Links:
- GitHub - https://github.com/snakers4/silero-models#text-to-speech
- Colab - https://colab.research.google.com/github/snakers4/silero-models/blob/master/examples_tts.ipynb
- Russian article - https://habr.com/ru/post/660565/
- English article - https://habr.com/ru/post/660571/
We have just released a brand new Russian speech synthesis model.
We have made a number of promises we kept:
- Model size reduced 2x;
- New models are 10x faster (!);
- We added flags to control stress;
- Now the models can make proper pauses;
- High quality voice added (and unlimited "random" voices);
- All speakers squeezed into the same model;
- Input length limitations lifted, now models can work with paragraphs of text;
- Pauses, speed and pitch can be controlled via SSML;
- Sampling rates of 8, 24 or 48 kHz are supported;
- Models are much more stable — they do not omit words anymore;
Next steps:
- Release models for the CIS languages, English, some European languages and Hindic languages
- Even further 2-4x speed up
- Updated stress model
- Phonemes support and and built-in voice transfer
Links:
- GitHub - https://github.com/snakers4/silero-models#text-to-speech
- Colab - https://colab.research.google.com/github/snakers4/silero-models/blob/master/examples_tts.ipynb
- Russian article - https://habr.com/ru/post/660565/
- English article - https://habr.com/ru/post/660571/
GitHub
GitHub - snakers4/silero-models: Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly…
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple - snakers4/silero-models
👍58🤔2👎1
Imagen — new neural network for picture generation from Google
TLDR: Competitor of DALLE was released.
Imagen — text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation. #Google key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model.
Website: https://imagen.research.google
#GAN #CV #DL #Dalle
TLDR: Competitor of DALLE was released.
Imagen — text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation. #Google key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model.
Website: https://imagen.research.google
#GAN #CV #DL #Dalle
🔥38👍23🤯3❤2😱1
Hi, our friends @mike0sv and @agusch1n just open-sourced MLEM - a tool that helps you deploy your ML models as part of the DVC ecosystem
It’s a Python library + Command line tool.
TLDR:
📦 MLEM can package an ML model into a Docker image or a Python package, and deploy it to Heroku (we made them promise to add SageMaker, K8s and Seldon-core soon :parrot:).
⚙️ MLEM saves all model metadata to a human-readable text file: Python environment, model methods, model input & output data schema and more.
💅 MLEM helps you turn your Git repository into a Model Registry with features like ML model lifecycle management.
Read more in release blogpost: https://dvc.org/blog/MLEM-release
Also, check out the project: https://github.com/iterative/mlem
And the website: https://mlem.ai
Guys are happy to hear your feedback, discuss how this could be helpful for you, how MLEM compares to MLflow, etc.
Ask in the comments!
#mlops #opensource #deployment #dvc
It’s a Python library + Command line tool.
TLDR:
📦 MLEM can package an ML model into a Docker image or a Python package, and deploy it to Heroku (we made them promise to add SageMaker, K8s and Seldon-core soon :parrot:).
⚙️ MLEM saves all model metadata to a human-readable text file: Python environment, model methods, model input & output data schema and more.
💅 MLEM helps you turn your Git repository into a Model Registry with features like ML model lifecycle management.
Read more in release blogpost: https://dvc.org/blog/MLEM-release
Also, check out the project: https://github.com/iterative/mlem
And the website: https://mlem.ai
Guys are happy to hear your feedback, discuss how this could be helpful for you, how MLEM compares to MLflow, etc.
Ask in the comments!
#mlops #opensource #deployment #dvc
🔥32👍13👎3🤔1
Forwarded from Spark in me (Alexander)
The Cat is on the Mat
Interesting approach to be combined with Ngram embeddings when span boundaries are fuzzy.
I guess can be used downstream with existing sentence parsers.
Such models can be rough and dirty, cheap to train and robust.
- https://explosion.ai/blog/spancat
Interesting approach to be combined with Ngram embeddings when span boundaries are fuzzy.
I guess can be used downstream with existing sentence parsers.
Such models can be rough and dirty, cheap to train and robust.
- https://explosion.ai/blog/spancat
explosion.ai
Spancat: a new approach for span labeling · Explosion
The SpanCategorizer is a spaCy component that answers the NLP community's need to
have structured annotation for a wide variety of labeled spans, including long
phrases, non-named entities, or overlapping annotations. In this blog post, we're
excited to talk…
have structured annotation for a wide variety of labeled spans, including long
phrases, non-named entities, or overlapping annotations. In this blog post, we're
excited to talk…
👍18👏2🤔1
Forwarded from Spark in me (Alexander)
DALL-E Mini Explained with Demo
Tech report:
- Financed by Google Cloud and HF, essentially an advertising campaign for JAX, 8 person team
- 27x smaller than the original, trained on a single TPU v3-8 for only 3 days + ~3 weeks for experiments, 400M params
- 30m image-text pairs, only 2m used to fine-tune the VQGAN encoder
- Could use preemptible TPU instances
- Pre-trained BART Encoder
- Pre-trained VQGAN encoder
- Pre-trained CLIP is used to select the best generated images
- (so the actual cost probably is actually ~1-2 orders of magnitude higher)
- (compare with 20k GPU days stipulated by Sber)
- The report is expertly written and easy to read
Tech report:
- Financed by Google Cloud and HF, essentially an advertising campaign for JAX, 8 person team
- 27x smaller than the original, trained on a single TPU v3-8 for only 3 days + ~3 weeks for experiments, 400M params
- 30m image-text pairs, only 2m used to fine-tune the VQGAN encoder
- Could use preemptible TPU instances
- Pre-trained BART Encoder
- Pre-trained VQGAN encoder
- Pre-trained CLIP is used to select the best generated images
- (so the actual cost probably is actually ~1-2 orders of magnitude higher)
- (compare with 20k GPU days stipulated by Sber)
- The report is expertly written and easy to read
W&B
DALL-E Mini Explained
Generate images from a text prompt in this interactive report: DALL-E Mini Explained, a reproduction of OpenAI DALL·E. Made by Boris Dayma using W&B
👍13❤1
Forwarded from Machinelearning
💬 Yandex: An Open-source Yet another Language Model 100B
YaLM 100B is trained for 2 terabyte of text: dataset the Pile and web-pages, including not only Wikipedia, news articles, and books, but also Github and arxiv.org. Yandex has applied the generative neural networks YaLM in the recent Y1 search update. Now they are already helping to give answers to searches in Yandex and Alice.
Github: https://github.com/yandex/YaLM-100B
@ai_machinelearning_big_data
YaLM 100B is trained for 2 terabyte of text: dataset the Pile and web-pages, including not only Wikipedia, news articles, and books, but also Github and arxiv.org. Yandex has applied the generative neural networks YaLM in the recent Y1 search update. Now they are already helping to give answers to searches in Yandex and Alice.
Github: https://github.com/yandex/YaLM-100B
@ai_machinelearning_big_data
👍18🤔17👎6🔥6
In 15 minutes, start the last section of DataFestOnline 2022.
[language of presentations - Russian]
Mikhail Neretin - Topic management in Kafka
Evgeniy Sorokin - Human and ML => collaboration
Olga Filippova - Data drift & Concept drift: How to monitor ML models in production
Dmitry Beloborodov - Matrix factorizations with embeddings of variable dimension
Stanislav Yarkin - Summarization Is All You Need: summarization in RecSys
Artem Trofimov - MLOps by DS forces
Possible: Secret Speaker - MLEM: Version and deploy your ML models following Hitops principles
Start at 11:00 MSK (UTC+3)
There is an opportunity to ask a question to the speaker
Where?
Come to the session -> https://live.ods.ai/
Room: Last chance
Password: followthepinkparrot
[language of presentations - Russian]
Mikhail Neretin - Topic management in Kafka
Evgeniy Sorokin - Human and ML => collaboration
Olga Filippova - Data drift & Concept drift: How to monitor ML models in production
Dmitry Beloborodov - Matrix factorizations with embeddings of variable dimension
Stanislav Yarkin - Summarization Is All You Need: summarization in RecSys
Artem Trofimov - MLOps by DS forces
Possible: Secret Speaker - MLEM: Version and deploy your ML models following Hitops principles
Start at 11:00 MSK (UTC+3)
There is an opportunity to ask a question to the speaker
Where?
Come to the session -> https://live.ods.ai/
Room: Last chance
Password: followthepinkparrot
👍21
Forwarded from Binary Tree
Today mimesis has been designated as a critical project on PyPI.
It's ain't much, but I feel warm when I think about how many people use think I built.
Thank you everyone!
P.S If you don't know what the hell mimesis is, then go and check it out. Maybe you'll find it useful for you.
#mimesis #pypi #python
It's ain't much, but I feel warm when I think about how many people use think I built.
Thank you everyone!
P.S If you don't know what the hell mimesis is, then go and check it out. Maybe you'll find it useful for you.
#mimesis #pypi #python
👍32❤4😁1
No Language Left Behind
Scaling Human-Centered Machine Translation
No Language Left Behind (NLLB) is a first-of-its-kind, AI breakthrough project that open-sources models capable of delivering high-quality translations directly between any pair of 200+ languages — including low-resource languages like Asturian, Luganda, Urdu and more. It aims to help people communicate with anyone, anywhere, regardless of their language preferences.
To enable the community to leverage and build on top of NLLB, the lab open source all they evaluation benchmarks (FLORES-200, NLLB-MD, Toxicity-200), LID models and training code, LASER3 encoders, data mining code, MMT training and inference code and our final NLLB-200 models and their smaller distilled versions, for easier use and adoption by the research community.
Paper: https://research.facebook.com/publications/no-language-left-behind/
Blog: https://ai.facebook.com/blog/nllb-200-high-quality-machine-translation/
GitHub: https://github.com/facebookresearch/fairseq/tree/26d62ae8fbf3deccf01a138d704be1e5c346ca9a
#nlp #translations #dl #datasets
Scaling Human-Centered Machine Translation
No Language Left Behind (NLLB) is a first-of-its-kind, AI breakthrough project that open-sources models capable of delivering high-quality translations directly between any pair of 200+ languages — including low-resource languages like Asturian, Luganda, Urdu and more. It aims to help people communicate with anyone, anywhere, regardless of their language preferences.
To enable the community to leverage and build on top of NLLB, the lab open source all they evaluation benchmarks (FLORES-200, NLLB-MD, Toxicity-200), LID models and training code, LASER3 encoders, data mining code, MMT training and inference code and our final NLLB-200 models and their smaller distilled versions, for easier use and adoption by the research community.
Paper: https://research.facebook.com/publications/no-language-left-behind/
Blog: https://ai.facebook.com/blog/nllb-200-high-quality-machine-translation/
GitHub: https://github.com/facebookresearch/fairseq/tree/26d62ae8fbf3deccf01a138d704be1e5c346ca9a
#nlp #translations #dl #datasets
👍39👎1
