AI in Science & Technology
438 subscribers
32 photos
13 videos
14 files
221 links
@ai_sci_tech
--------
Linkedin group:
“Ai & BigData"
https://www.linkedin.com/groups/8721739/

Telegram group for question and answer:
@ml_in_scienc

Github repository:
https://github.com/Machine-Learning-in-Science/pedagogical
Download Telegram
‍ ‍‍ ❇️ در مقاله ای بسیار جالب Samsung AI شبکه عصبی ای را طراحی کرده است که از روی فریم های ویدیوی واقعی صحبت کردن یک فرد (حتی یک شات) یادگیری انجام میدهد و سپس آن را به یک پرتره منتقل میکند و به آن جان می بخشد.


❇️ https://arxiv.org/abs/1905.08233
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
💠 مجموعه مقالاتی دنباله دار و متوالی به زبانی ساده و با بیانی بسیار عالی از وبسایت مدیوم برای کسانی که دوست دارند خیلی سریع با دنیای یادگیری ماشین و مثالهایی واقعی از آن به همراه کد نویسی آشنا بشوند. در انتها در بخش ضمیمه هم منابع بسیار جالب و مفید معرفی شده است.


💠 https://medium.com/machine-learning-for-humans/why-machine-learning-matters-6164faf1df12

Roadmap

❇️ Part 1: Why Machine Learning Matters.
The big picture of artificial intelligence and machine learning — past, present, and future.

❇️ Part 2.1: Supervised Learning. Learning with an answer key.
Introducing linear regression, loss functions, overfitting, and gradient descent.

❇️ Part 2.2: Supervised Learning II.
Two methods of classification: logistic regression and SVMs.

❇️ Part 2.3: Supervised Learning III.
Non-parametric learners: k-nearest neighbors, decision trees, random forests. Introducing cross-validation, hyperparameter tuning, and ensemble models.

❇️ Part 3: Unsupervised Learning.
Clustering: k-means, hierarchical. Dimensionality reduction: principal components analysis (PCA), singular value decomposition (SVD).
❇️ Part 4: Neural Networks & Deep Learning.
Why, where, and how deep learning works. Drawing inspiration from the brain. Convolutional neural networks (CNNs), recurrent neural networks (RNNs). Real-world applications.

❇️ Part 5: Reinforcement Learning.
Exploration and exploitation. Markov decision processes. Q-learning, policy learning, and deep reinforcement learning. The value learning problem.

☯️ Appendix: The Best Machine Learning Resources. A curated list of resources for creating your machine learning curriculum.
❇️ مصاحبه در دانشگاه استافورد درباره هوش مصنوعی با حضور یووال نوح هراری (نویسنده کتاب انسان خردمند) و فیی-فیی لی (خالق ImageNet)

❇️ ۴ سوال که بر همه ما اثر می گذارد.

More questions than answers were generated during a recent conversation at Stanford University between a pair of Artificial Intelligence giants — Yuval Noah Harari and Fei-Fei Li. Nicholas Thompson, editor in chief of WIRED, moderated the 90-minute conversation in the packed Memorial Auditorium, filled to its 1705-seat capacity.

🌍 https://towardsdatascience.com/yuval-noah-harari-and-fei-fei-li-on-ai-90d9a8686cc5
❇️ دروس رایگان در سطوح مقدماتی، متوسط و پیشرفته یادگیری ماشین وبسایت Kaggle

❇️ Kaggle FREE elementary, intermediate and advanced ML courses:

💠سطح مقدماتی
Python:
🌍 https://www.kaggle.com/learn/python
Intro to Machine Learning :
🌍 https://www.kaggle.com/learn/intro-to-machine-learning


💠 سطح متوسط
Intermediate Machine Learning:
🌍 https://www.kaggle.com/learn/intermediate-machine-learning


💠 سطح پیشرفته
Machine Learning Explainability:
🌍 https://www.kaggle.com/learn/machine-learning-explainability

💠 همه ۱۱ درس یادگیری ماشین

All 11 ML courses:
🌍 https://www.kaggle.com/learn/overview
Forwarded from ziSTartup
CB-Insights_AI-Trends-2019-iotreport.pdf
5.7 MB
#report
#ai
❇️ گرایش های هوش مصنوعی سال ۲۰۱۹
❇️ Artificial Intelligence Trends 2019
کل کتاب

💠 Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow💎SECOND EDITION💎
Concepts, Tools, and Techniques to Build Intelligent Systems
❇️ by: Aurélien Géron

برای ترجمه پوشش داده شده است.
با تشکر از همه عزیزانی که در این ترجمه شرکت کرده اند. 😊👍🙏🌺
This media is not supported in your browser
VIEW IN TELEGRAM
❇️ Argo.ai has released a very cool new dataset called Argoverse which can be used for computer vision/ML research and in particular to advance self-driving cars technology.

The datasets includes:
- Two HD maps with total 290km of mapped roadway (Miami & Pittsburgh)
- 3D tracking annotations for 113 scenes with 11,319 tracked objects
- 327,793 interesting vehicle trajectories from 1000 driving hours which is useful for motion forecasting
- An API to connect the map data with sensor information

Check it out!

📝 Article: https://lnkd.in/dJFeRFK
🚗 Dataset: https://lnkd.in/dqCTwf2
🔤 Github: https://lnkd.in/daay-ze
0.pdf
1.1 MB
❇️ Python for Data Analysis (47 pages) 💠 Katia Oleinikو Boston University