Deep Reinforcement Learning and the Entity Neural Network (ENN) project! It's all about making RL easier to apply in complex simulated environments. Check it out:
https://clemenswinter.com/2023/04/14/entity-based-reinforcement-learning/
Deep Reinforcement Learning and the Entity Neural Network (ENN) project! It's all about making RL easier to apply in complex simulated environments.
The main hurdle for broader RL adoption is the lack of user-friendly tooling and infrastructure. ENN aims to bridge this gap with libraries that cut down on engineering effort, computational cost, and required expertise.Meet the enn-trainer RL framework! It integrates smoothly with complex simulators without the need for custom training code or network architectures.
It's never been this simple to implement RL in your projects.Here's something cool: RL agents produced by enn-trainer can run in real-time on a CPU inside web browsers! This opens up new possibilities for RL applications on the web. https://cswinter.github.io/bevy-starfighter/
#مقاله
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
https://clemenswinter.com/2023/04/14/entity-based-reinforcement-learning/
Deep Reinforcement Learning and the Entity Neural Network (ENN) project! It's all about making RL easier to apply in complex simulated environments.
The main hurdle for broader RL adoption is the lack of user-friendly tooling and infrastructure. ENN aims to bridge this gap with libraries that cut down on engineering effort, computational cost, and required expertise.Meet the enn-trainer RL framework! It integrates smoothly with complex simulators without the need for custom training code or network architectures.
It's never been this simple to implement RL in your projects.Here's something cool: RL agents produced by enn-trainer can run in real-time on a CPU inside web browsers! This opens up new possibilities for RL applications on the web. https://cswinter.github.io/bevy-starfighter/
#مقاله
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
❤2
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning
abs: arxiv.org/abs/2304.05613
abs: arxiv.org/abs/2304.05613
❤2👍1
ده #ایده_جذاب که در هفته گذشته منتشر شد.
🔸 Segment Anything
▪️ presents a set of resources to establish foundational models for image segmentation; releases the largest segmentation dataset with over 1 billion masks on 11M licensed images; the model’s zero-shot performance is competitive with or even superior to fully supervised results.
🔸 Instruction Tuning with GPT-4
▪️ presents GPT-4-LLM, a "first attempt" to use GPT-4 to generate instruction-following data for LLM fine-tuning; the dataset is released and includes 52K unique English and Chinese instruction-following data; the dataset is used to instruction-tune LLaMA models which leads to superior zero-shot performance on new tasks.
🔸 Eight Things to Know about Large Language Models
▪️ discusses important considerations regarding the capabilities and limitations of LLMs.
🔸 A Survey of Large Language Models
▪️ a new 50 pages survey on large language models.
🔸 Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data
▪️ an open-source chat model fine-tuned with LoRA. Leverages 100K dialogs generated from ChatGPT chatting with itself; it releases the dialogs along with 7B, 13B, and 30B parameter models.
🔸 Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
▪️ a new benchmark of 134 text-based Choose-Your-Own-Adventure games to evaluate the capabilities and unethical behaviors of LLMs.
🔸 Better Language Models of Code through Self-Improvement
▪️ generates pseudo data from knowledge gained through pre-training and fine-tuning; adds the data to the training dataset for the next step; results show that different frameworks can be improved in performance using code-related generation tasks.
🔸 Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models
▪️ an overview of applications of ChatGPT and GPT-4; the analysis is done on 194 relevant papers and discusses capabilities, limitations, concerns, and more
🔸 Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
▪️ a suite for analyzing LLMs across training and scaling; includes 16 LLMs trained on public data and ranging in size from 70M to 12B parameters.
🔸 SegGPT: Segmenting Everything In Context
▪️unifies segmentation tasks into a generalist model through an in-context framework that supports different kinds of data.
#مقاله
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
🔸 Segment Anything
▪️ presents a set of resources to establish foundational models for image segmentation; releases the largest segmentation dataset with over 1 billion masks on 11M licensed images; the model’s zero-shot performance is competitive with or even superior to fully supervised results.
🔸 Instruction Tuning with GPT-4
▪️ presents GPT-4-LLM, a "first attempt" to use GPT-4 to generate instruction-following data for LLM fine-tuning; the dataset is released and includes 52K unique English and Chinese instruction-following data; the dataset is used to instruction-tune LLaMA models which leads to superior zero-shot performance on new tasks.
🔸 Eight Things to Know about Large Language Models
▪️ discusses important considerations regarding the capabilities and limitations of LLMs.
🔸 A Survey of Large Language Models
▪️ a new 50 pages survey on large language models.
🔸 Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data
▪️ an open-source chat model fine-tuned with LoRA. Leverages 100K dialogs generated from ChatGPT chatting with itself; it releases the dialogs along with 7B, 13B, and 30B parameter models.
🔸 Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
▪️ a new benchmark of 134 text-based Choose-Your-Own-Adventure games to evaluate the capabilities and unethical behaviors of LLMs.
🔸 Better Language Models of Code through Self-Improvement
▪️ generates pseudo data from knowledge gained through pre-training and fine-tuning; adds the data to the training dataset for the next step; results show that different frameworks can be improved in performance using code-related generation tasks.
🔸 Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models
▪️ an overview of applications of ChatGPT and GPT-4; the analysis is done on 194 relevant papers and discusses capabilities, limitations, concerns, and more
🔸 Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
▪️ a suite for analyzing LLMs across training and scaling; includes 16 LLMs trained on public data and ranging in size from 70M to 12B parameters.
🔸 SegGPT: Segmenting Everything In Context
▪️unifies segmentation tasks into a generalist model through an in-context framework that supports different kinds of data.
#مقاله
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍3❤1
کسایی که قصد فراگیری NLP دارند و مشخصا قضد فهمیدن و درک اهمیت Tranformersها را دارند این مقاله بهترین رفرنس یادگیری است.
▪️ چرا این مقاله مهم است؟ چون شما را با معماری و قابلیتهاش آشنا میکند. اینکه چطور شد به مدلهایی مانند BERT و GPT رسیدند.
▪️ هدف این مقاله این است که شما را با Neural machine translation (NMT) آشنا میکند و...
اینکه معماری ترنسفومرها encoder-decoder است .
در این مقاله BERT/GPT تنها برخی از کارهایی است که ترنسفورمر میتواند داشته باشد و images, graph networks, GANs در برخی کارهای دیگر هم میتواند نتایج بیشتری از مسایل را نشان دهد.
Attention Is All You Need
https://arxiv.org/abs/1706.03762
#مقاله #ایده_جذاب #منابع
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
▪️ چرا این مقاله مهم است؟ چون شما را با معماری و قابلیتهاش آشنا میکند. اینکه چطور شد به مدلهایی مانند BERT و GPT رسیدند.
▪️ هدف این مقاله این است که شما را با Neural machine translation (NMT) آشنا میکند و...
اینکه معماری ترنسفومرها encoder-decoder است .
در این مقاله BERT/GPT تنها برخی از کارهایی است که ترنسفورمر میتواند داشته باشد و images, graph networks, GANs در برخی کارهای دیگر هم میتواند نتایج بیشتری از مسایل را نشان دهد.
Attention Is All You Need
https://arxiv.org/abs/1706.03762
#مقاله #ایده_جذاب #منابع
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍6❤1🔥1
Understanding Diffusion Models: A Unified Perspective
Diffusion models are the engine behind novel image generative systems. This tutorial provides an intuitive and comprehensive understanding of diffusion models.
Paper: arxiv.org/abs/2208.11970
https://calvinyluo.com/2022/08/26/diffusion-tutorial.html
Diffusion models are the engine behind novel image generative systems. This tutorial provides an intuitive and comprehensive understanding of diffusion models.
Paper: arxiv.org/abs/2208.11970
https://calvinyluo.com/2022/08/26/diffusion-tutorial.html
arXiv.org
Understanding Diffusion Models: A Unified Perspective
Diffusion models have shown incredible capabilities as generative models; indeed, they power the current state-of-the-art models on text-conditioned image generation such as Imagen and DALL-E 2....
👍2❤1
MiniGPT-4 is pretty astonishing: an AI chatbot you can use to ask questions about an image (a feature that's been promised but not yet shipped by GPT-4), building on top of the Vicuna-13B LLM (derived from LLaMA) and BLIP-2 vision-language
model minigpt-4.github.io
#مقاله
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
model minigpt-4.github.io
#مقاله
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
What are some design patterns in machine learning systems?
Here are a few I've seen:
1. Cascade: Break a complex problem into simpler problems. Each subsequent model focuses on more difficult or specific problems.
Stack Exchange has a cascade of defenses against spam:
https://stackoverflow.blog/2020/06/25/how-does-spam-protection-work-on-stack-exchange/
2. Reframing: Redefine the original problem, target, or input to make the problem easier to solve.
Sequential recsys reframed the paradigm from co-occurrence (matrix factorization) to predict-the-next-event (e.g., transformers).
arxiv.org/abs/1905.06874
3. Human-in-the-loop: Collect labels from users, annotation services, or domain experts.
Stack Exchange lets users flag spam, and LinkedIn lets users report messages as harassment:
https://engineering.linkedin.com/blog/2020/fighting-harassment
Recently, LLMs are used in labeling too:
ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks:
arxiv.org/abs/2303.15056
4. Data Augmentation: Synthetically increase the size and diversity of training data to improve model generalization and reduce overfitting.
DoorDash varied sentence order and randomly removed information such as menu category:
https://doordash.engineering/2020/08/28/overcome-the-cold-start-problem-in-menu-item-tagging/
5. Data flywheel: Positive feedback loop where more data improves ML models, which leads to more users and data.
Tesla collects data via cars, finds and labels errors, retrains models, and then deploys to their cars which gather more data.
Potentially nitpicky but competitive advantage in AI goes not so much to those with data but those with a data engine: iterated data aquisition, re-training, evaluation, deployment, telemetry. And whoever can spin it fastest. Slide from Tesla to ~illustrate but concept is general.
6. Business Rules: Adding logic or constraints based on domain knowledge and/or business requirements to augment or adjust the output of ML models
Twitter has various hand-tuned weights when predicting engagement probabilities:
https://github.com/twitter/the-algorithm-ml/tree/main/projects/home/recap
A few more that I'll cover in a write-up:
• Aggregate raw data once: To reduce compute cost
• Evaluate before deploy: For safety and reliability
• Hard mining: To better learn difficult instances
#مقاله #خبر
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
Here are a few I've seen:
1. Cascade: Break a complex problem into simpler problems. Each subsequent model focuses on more difficult or specific problems.
Stack Exchange has a cascade of defenses against spam:
https://stackoverflow.blog/2020/06/25/how-does-spam-protection-work-on-stack-exchange/
2. Reframing: Redefine the original problem, target, or input to make the problem easier to solve.
Sequential recsys reframed the paradigm from co-occurrence (matrix factorization) to predict-the-next-event (e.g., transformers).
arxiv.org/abs/1905.06874
3. Human-in-the-loop: Collect labels from users, annotation services, or domain experts.
Stack Exchange lets users flag spam, and LinkedIn lets users report messages as harassment:
https://engineering.linkedin.com/blog/2020/fighting-harassment
Recently, LLMs are used in labeling too:
ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks:
arxiv.org/abs/2303.15056
4. Data Augmentation: Synthetically increase the size and diversity of training data to improve model generalization and reduce overfitting.
DoorDash varied sentence order and randomly removed information such as menu category:
https://doordash.engineering/2020/08/28/overcome-the-cold-start-problem-in-menu-item-tagging/
5. Data flywheel: Positive feedback loop where more data improves ML models, which leads to more users and data.
Tesla collects data via cars, finds and labels errors, retrains models, and then deploys to their cars which gather more data.
Potentially nitpicky but competitive advantage in AI goes not so much to those with data but those with a data engine: iterated data aquisition, re-training, evaluation, deployment, telemetry. And whoever can spin it fastest. Slide from Tesla to ~illustrate but concept is general.
6. Business Rules: Adding logic or constraints based on domain knowledge and/or business requirements to augment or adjust the output of ML models
Twitter has various hand-tuned weights when predicting engagement probabilities:
https://github.com/twitter/the-algorithm-ml/tree/main/projects/home/recap
A few more that I'll cover in a write-up:
• Aggregate raw data once: To reduce compute cost
• Evaluate before deploy: For safety and reliability
• Hard mining: To better learn difficult instances
#مقاله #خبر
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
چگونه از #چتجیپیتی چیزی بخوایم؟
شاید خواسته باشید از #ChatGPT کاری بخواید، ولی ندونید چطوری بپرسید، یا میپرسید ولی جواب مورد نظرتون رو نمیگیرید.
درخواست یا اصطلاحا Prompt درست برای گرفتن جواب درست بسیار مهمه
خب شما میتونید از خودش بخواید واستون Prompt رو بنویسه.
شما میتونید با یه Loop ساده از چتجیپیتی بخواید هر بار اون Prompt رو پربار تر و نزدیک تر به هدفی که میخواید بکنه.
لوپ ما سه قسمت داره:
1. اول Prompt فعلی رو با استفاده از اطلاعاتی که گرفتی ادیت کن
2. پیشنهاد بده چی کجا باشه
3. ازم سوال مربوط بپرس
این چرخه همینطور ادامه پیدا میکنه تا پرامپت شما پربار تر و دقیق تر بشه
به طور مثال اینجا خواستیم تا در رابطه با تیم فوتبال آث میلان واسمون یه مقاله بنویسه:
هر بار از شما چنتا سوال میپرسه تا اون پرامپت اولیه رو بهتر و بهتر کنه، هرچی بیشتر برید جلو و جزییات بیشتری بهش بدید جواب قشنگتری میگیرید، به خاطر داشته باشید تا صبح ازتون سوال میپرسه پس هرجا احساس کردید کافیه ادامه ندید:
در انتها، کافیه که اون قسمت Revised Prompt تنها یا همراه با پیشنهادات رو توی یه چت جدید کپی کنید و از نتیجه لذت ببرید!
اون Prompt Generator رو از اینجا میتونید کپی کنید:
https://docs.google.com/document/d/1ve9hpyJ5JVWgNYZkaiFyNFUEDxJ113xtBuNztCjYhOA/edit?usp=drivesdk
#مقاله #خبر
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
شاید خواسته باشید از #ChatGPT کاری بخواید، ولی ندونید چطوری بپرسید، یا میپرسید ولی جواب مورد نظرتون رو نمیگیرید.
درخواست یا اصطلاحا Prompt درست برای گرفتن جواب درست بسیار مهمه
خب شما میتونید از خودش بخواید واستون Prompt رو بنویسه.
شما میتونید با یه Loop ساده از چتجیپیتی بخواید هر بار اون Prompt رو پربار تر و نزدیک تر به هدفی که میخواید بکنه.
لوپ ما سه قسمت داره:
1. اول Prompt فعلی رو با استفاده از اطلاعاتی که گرفتی ادیت کن
2. پیشنهاد بده چی کجا باشه
3. ازم سوال مربوط بپرس
این چرخه همینطور ادامه پیدا میکنه تا پرامپت شما پربار تر و دقیق تر بشه
به طور مثال اینجا خواستیم تا در رابطه با تیم فوتبال آث میلان واسمون یه مقاله بنویسه:
هر بار از شما چنتا سوال میپرسه تا اون پرامپت اولیه رو بهتر و بهتر کنه، هرچی بیشتر برید جلو و جزییات بیشتری بهش بدید جواب قشنگتری میگیرید، به خاطر داشته باشید تا صبح ازتون سوال میپرسه پس هرجا احساس کردید کافیه ادامه ندید:
در انتها، کافیه که اون قسمت Revised Prompt تنها یا همراه با پیشنهادات رو توی یه چت جدید کپی کنید و از نتیجه لذت ببرید!
اون Prompt Generator رو از اینجا میتونید کپی کنید:
https://docs.google.com/document/d/1ve9hpyJ5JVWgNYZkaiFyNFUEDxJ113xtBuNztCjYhOA/edit?usp=drivesdk
#مقاله #خبر
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍1
برای فهم و درک کامل مفاهیم یادگیری ماشین از پایه این مقاله یا کتاب رو پیشنهاد میدم هم جدید هست و با موضوعاتی جامعتر
Exercises in Machine Learning
linear algebra, optimization, graphical models
arxiv.org/abs/2206.13446
پ.ن: کتاب دکتر Hal Daume یکی دیگر از منابع تئوری #یادگیری_ماشین است.
🔸 A Course in Machine Learning
#کتاب #مقاله #مبتدی
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
Exercises in Machine Learning
linear algebra, optimization, graphical models
arxiv.org/abs/2206.13446
پ.ن: کتاب دکتر Hal Daume یکی دیگر از منابع تئوری #یادگیری_ماشین است.
🔸 A Course in Machine Learning
#کتاب #مقاله #مبتدی
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍4❤2
مدلی جدیدی دیگر منتشر شد
launching Sabiá-65B, a large language model pretrained on Portuguese with slightly better performance than ChatGPT-3.5 on 14 Portuguese datasets. In a few weeks, we will make an API available for researchers.
More details: arxiv.org/pdf/2304.07880
#مقاله
launching Sabiá-65B, a large language model pretrained on Portuguese with slightly better performance than ChatGPT-3.5 on 14 Portuguese datasets. In a few weeks, we will make an API available for researchers.
More details: arxiv.org/pdf/2304.07880
#مقاله
❤2
رتبه بندی مبدِع ترین شرکتهای آمریکایی
https://fortune.com/ranking/americas-most-innovative-companies/
#هوش_مصنوعی #خبر
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
https://fortune.com/ranking/americas-most-innovative-companies/
#هوش_مصنوعی #خبر
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍2
ChatGPT applications, opportunities, and threats.
arxiv.org/abs/2304.09103
#مقاله #مبتدی
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
arxiv.org/abs/2304.09103
#مقاله #مبتدی
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍2
My lab is hiring a full-time research staff position! We are looking for someone with experience in neuroimaging analysis to assist in studies of brain-behavior evolution in dogs, foxes, primates, and humans. Come join our team! bit.ly/61689BR
👍1
Evaluating Verifiability of LLM-Powered Search Engines
-Human eval of Bing Chat, NeevaAI, perplexity ai, YouChat
-Responses are fluent but frequently contain unsupported statements & inaccurate citations
-51.5% of sentences fully supported by citations
arxiv.org/abs/2304.09848
-Human eval of Bing Chat, NeevaAI, perplexity ai, YouChat
-Responses are fluent but frequently contain unsupported statements & inaccurate citations
-51.5% of sentences fully supported by citations
arxiv.org/abs/2304.09848
وبسایت Shecodes به ایرانیا بورسیه میده علاقمندان براش اقدام کنن
shecodesfoundation.org/candidates/new
#خبر #برنامه_نویسی
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
shecodesfoundation.org/candidates/new
#خبر #برنامه_نویسی
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
👍1