با دیکشنری 40 تایی که از تصاویر مختلف اشخاص داشته، هویت شخص شطرنجی شده را تشخیص داده

کتابخانه یادگیری عمیق tensorflow
این کتابخانه ی pythonی
توسط گوگل پشتیبانی میشه و بشدت داره رشد میکنه
https://www.tensorflow.org
کلا گزینه ی خیلی خوبی برای machine learning، شبکه عصبی و یادگیری عمیقه

مثالهای ساده ی آموزشی:
https://github.com/aymericdamien/TensorFlow-Examples

شبکه عصبی های کاربردی نسبتا جدید مثل cnn و lstm و ... هم تو کتابخونه های هست و ساپورت میکند...

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

https://github.com/songrotek/Deep-Learning-Papers-Reading-Roadmap/

neuralnetworksanddeeplearning.com

#deep_learning #neural_network #book

کتاب خوب برای یادگیری عمیق و شبکه عصبی

کتاب رایگان و آنلاین انتشارات MIT در مورد یادگیری عمیق:
An MIT Press book
Ian Goodfellow and Yoshua Bengio and Aaron Courville

The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free.

deeplearningbook.org

#site #deep_learning #machine_learning
good online book for deep learning

یک کتاب خوب آنلاین برای یادگیری عمیق ماشین (deep learning)

سخنرانی Yann Lecun مدیر AI research lab شرکت Facebook در کنفرانس NIPS:
https://drive.google.com/file/d/0BxKBnD5y2M8NREZod0tVdW5FLTQ/view

طراحی CNN در متلب 2016 به همین راحتی انجام می شود:

https://www.mathworks.com/help/nnet/ref/layer-class.html

نسخه اولیه ( draft version ) کتاب یادگیری ماشین Andrew Ng
#کتاب

Amazon go
کاربرد هوش مصنوعی، بینایی ماشین و یادگیری عمیق در خرید ساده 👌


How does Amazon Go work?
Our checkout-free shopping experience is made possible by the same types of technologies used in self-driving cars: #computer_vision, sensor fusion, and #deep_learning. Our Just Walk Out technology automatically detects when products are taken from or returned to the shelves and keeps track of them in a virtual cart. When you’re done shopping, you can just leave the store. Shortly after, we’ll charge your Amazon account and send you a receipt.

https://www.amazon.com/b?ie=UTF8&node=16008589011

حضور جالب و خاص Andrew Ng در TED 😊

A Conversation with Andrew Ng | Andrew Ng | TEDxBoston

دکتر َAndrew NG بیش از 100 مقاله تحقیقاتی در یادگیری ماشین، رباتیک و زمینه های مرتبط منتشر کرده است.
در سال 2013 نام وی در لیست 100 نفر از با نفوذ ترین افراد در جهان قرارگرفت.
مدارک تحصلی وی از دانشگاه Carnegie Mellon ، MIT و دانشگاه Berkeley کالیفرنیا است. و در حال حاضر استاد دانشگاه استفورد است.

بازسازی صحنه های فیلم مشاهده شده توسط فرد با پردازش فعالیت های ناحیه ی بینایی مغز
آیا میتوان یک روز رویاها و خواب ها را با این تکنولوژی ضبط کرد و به صورت فیلم بازیابی کرد؟!
UC Berkeley researchers have succeeded in #decoding and #reconstructing people's dynamic #visual experiences.

The #brain activity recorded while subjects viewed a set of film clips was used to create a computer program that learned to associate visual patterns in the movie with the corresponding brain activity. The brain activity evoked by a second set of clips was used to test the movie reconstruction algorithm. This was done by feeding 18 million seconds of random YouTube videos into the computer program so that it could predict the brain activity that each film clip would most likely evoke in each subject. Using the new computer model, researchers were able to decode brain signals generated by the films and then reconstruct those moving images.

Eventually, practical applications of the technology could include a better understanding of what goes on in the minds of people who cannot communicate verbally, such as stroke victims, coma patients and people with neurodegenerative diseases. It may also lay the groundwork for brain-machine devices that would allow people with cerebral palsy or paralysis, for example, to guide computers with their minds.

The lead author of the study, published in Current Biology on September 22, 2011, is Shinji Nishimoto, a post-doctoral researcher in the laboratory of Professor Jack Gallant, neursoscientist and coauthor of the study. Other coauthors include Thomas Naselaris with UC Berkeley's Helen Wills #Neuroscience Institute, An T. Vu with UC Berkeley's Joint Graduate Group in Bioengineering, and Yuval Benjamini and Professor Bin Yu with the UC Berkeley Department of Statistics.
more:
http://news.berkeley.edu/2011/09/22/brain-movies/

'Your #face is big data:' The noscript of this photographer's experiment says it all...


http://images.techhive.com/images/article/2016/04/your-face-is-big-data-100655649-large.jpg

http://www.pcworld.com/article/3055305/analytics/your-face-is-big-data-the-noscript-of-this-photographers-experiment-says-it-all.html


یه مرد روسی در مترو از مسافرین عکس گرفته، سپس با الگوریتمهای تشخیص چهره اکانت شبکه های اجتماعی آنها را پیدا کرده،
تو سایتش نیز چند نمونه از مسافرا را قرار داده...

https://birdinflight.com/ru/vdohnovenie/fotoproect/06042016-face-big-data.html

#face_recognition

21 #Deep_Learning #Videos, #Tutorials & #Courses on Youtube from 2016:

https://www.analyticsvidhya.com/blog/2016/12/21-deep-learning-videos-tutorials-courses-on-youtube-from-2016/

Deep learning
Yann LeCun, Yoshua Bengio & Geoffrey Hinton
http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html

#Deep_learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object #recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep #convolutional nets have brought about breakthroughs in processing #images, #video, #speech and #audio, whereas #recurrent nets have shone light on sequential data such as #text and speech.

Deep Residual Learning for Image Recognition
https://arxiv.org/pdf/1512.03385v1.pdf

شبکه عمیق 152 لایه...