آموزش Data Science دانشگاه هاروارد

1. Lecture notes
2. R code, Python notebooks
3. Lab material
4. Advanced sections

https://harvard-iacs.github.io/2019-CS109A/pages/materials.html

#منابع_پیشنهادی #منابع #علم_داده #آمار

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

Machine Learning with Conformal Prediction for Predictive Maintenance tasks in Industry 4.0

https://www.diva-portal.org/smash/get/diva2:1765779/FULLTEXT01.pdf

https://github.com/valeman/awesome-conformal-prediction

#منابع_پیشنهادی #منابع #یادگیری_ماشین #مقاله

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

چطوری با AI پاورپوینت خودمونو تهیه کنیم؟!

https://twitter.com/itsPaulAi/status/1670061522528137216?t=P04-K8mpYGx0N-kMXYNysg&s=19

#هوش_مصنوعی #خبر

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

در هفته گذشته چه ایده های منتشر شده است:

1) Voicebox - an all-in-one generative speech model; it can synthesize speech across 6 languages; it can perform noise removal, content editing, style conversion, and more; it's 20x faster than current models and outperforms single-purpose models through in-context learning.

2) FinGPT - an open-source LLM for the finance sector; it takes a data-centric approach, providing researchers & practitioners with accessible resources to develop FinLLMs.

3) Crowd Workers Widely Use Large Language Models for Text Production Tasks - estimates that 33-46% of crowd workers on MTurk used LLMs when completing a text production task.

4) Reliability of Watermarks for LLMs - watermarking is useful to detect LLM-generated text and potentially mitigate harms; this work studies the reliability of watermarking for LLMs and finds that watermarks are detectable even when the watermarked text is re-written by humans or paraphrased by another non-watermarked LLM.

5. Applications of Transformers - a new survey paper highlighting major applications of Transformers for deep learning tasks; includes a comprehensive list of Transformer models.

6) Benchmarking NN Training Algorithms - it’s currently challenging to properly assess the best optimizers to train neural networks; this paper presents a new benchmark, AlgoPerf, for benchmarking neural network training algorithms using realistic workloads.

7) Unifying LLMs & Knowledge Graphs - provides a roadmap for the unification of LLMs and KGs; covers how to incorporate KGs in LLM pre-training/inferencing, leverage LLMs for KG tasks such as question answering, and enhance both KGs and LLMs for bidirectional reasoning.

8) Augmenting LLMs with Long-term Memory - proposes a framework to enable LLMs to memorize long history; it’s enhanced with memory-augmented adaptation training to memorize long past context and use long-term memory for language modeling; achieves improvements on memory-augmented in-context learning over LLMs.

9) TAPIR - enables tracking any queried point on any physical surface throughout a video sequence; outperforms all baselines and facilitates fast inference on long and high-resolution videos (track points faster than real-time when using modern GPUs).

10) Mind2Web - a new dataset for evaluating generalist agents for the web; contains 2350 tasks from 137 websites over 31 domains; it enables testing generalization ability across tasks and environments, covering practical use cases on the web.

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

Demystifying GPT Self-Repair for Code Generation

We've seen a couple of papers showing the promise of self-repair in code generation. This paper finds that modest performance gains are seen when using GPT-4 for textual feedback.

Another interesting finding: significant performance is seen when GPT-4 provides feedback to GPT-3.5 and expert human programmers provide feedback to programs generated by GPT-4.

Feedback seems to be crucial for self-repair but I sense there is a lot more work to be done when using model-generated feedback. Human feedback is still a strong approach and more investigation is needed to figure out when to rely on human intervention.

arxiv.org/abs/2306.09896

نظرسنجی جالبی که منتشر شده
https://survey.stackoverflow.co/2023/

قبلتر راجب این ابزار صحبتهایی شده حالا به شکل و روشهای دیگه ای مشغول بهینه‌سازی این این مدل هستند
Fast Segment Anything
https://huggingface.co/papers/2306.12156

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

ایده هایی که تاکنون در حال انتشار هستند یک بخشی از حل اونها RLHF هستش حال سوال اینست که چطور کار میکنه !؟

Why does reinforcement learning from human feedback (RLHF) work?

https://www.interconnects.ai/p/how-rlhf-works

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

How to do continual learning on a data stream without restrictions on network architecture?

proposed framework learns a stream of learners with diverse architectures.


🔸 Heterogeneous Continual Learning

🔸 Youtube Paper CL

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

قبلتر راجب این ایده و موضوع مقالاتی منتشر کردم با پیگیری هشتگ #ایده_جذاب میتونید به موضوعات جالبی برسید.

🔸 Image and Language Understanding from Pixels Only

🔸 GitHub
🔸 Google Colab

🔸 پست های قبلی

#مقاله

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

https://huggingface.co/papers/2306.11932

#مقاله

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

بهترین مقالات برگزیده در کنفرانس CVPR 2023
1) Visual Programming for Compositional Visual Reasoning
https://prior.allenai.org/projects/visprog

2) Planning-oriented Autonomous Driving
https://opendrivelab.github.io/UniAD/

3) DynIBaR Neural Dynamic Image-Based Rendering
https://dynibar.github.io/

4) 3D Registration with Maximal Cliques
https://arxiv.org/abs/2305.10854

5) DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
https://dreambooth.github.io/

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

یک کار علمی بسیار ارزشمند جهت شناسایی موقعیت کاربران موبایل توسط پیامک!

در این روش مهاجم تعدادی پیامک به شماره هدف میفرسته وبه کمک زمان بین ارسال پیامک و دریافت پیام تایید ارسال آن تولیدشده توسط اپراتور قادر به شناسایی مکان کاربر هدف با دقتی تا ۹۶% هستند.
Freaky Leaky SMS: Extracting User Locations by Analyzing SMS Timings

https://arxiv.org/abs/2306.07695

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind

ابزارهایی که در لینوکس به درد #برنامه_نویس ها میخوره

https://courses.cs.washington.edu/courses/cse391/23sp/

ترم از قلم افتاده از دانشگاه mit
https://missing.csail.mit.edu/

#منابع #منابع_پیشنهادی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind