دموی بازشناسی چهره شرکت Baidu توسط Andrew Ng
این مدل با تصویر فرد فریب نمیخورد
Face Recognition demo - Baidu's face-enabled entrance
#face #Andrew_Ng

مطالب مورد نیاز برای کورس دیپ لرنینگ andrew ng.
اسلایدها - نوت بوک ها - کوییزهای 4 کورس اول از deep learning specialization مربوط به andrew ng بدون پاسخ و با محتوای ورد نیاز شامل تست کیس ها...

deeplearning.ai , By #Andrew_Ng, All slide and notebook + data (without solution) and video link

https://github.com/shahariarrabby/deeplearning.ai

#آموزش #منابع #دانلود_کورس

همان طور که میدانید پروفسور Andrew Ng پنج کورس یادگیری عمیق در سایت coursera تحت عنوان deep learning specialization ارائه کرده اند.
https://www.coursera.org/specializations/deep-learning
در صورتی که تمایلی ندارید دراین دوره ها عضو شوید, میتوانید فیلم ها و محتوای آموزشی این دوره ها را یکجا دانلود کنید.
—---------—

دانلود دوره اول – شبکه های عصبی Andrew Ng
http://muniversity.ir/neural-networks-deep-learning/

دانلود دوره دوم - ( تنظیم پارامترهای شبکه عصبی)
http://muniversity.ir/deep-neural-network/

دانلود دوره سوم - انجام پروژه های یادگیری ماشین

http://muniversity.ir/machine-learning-projects/

دانلود دوره چهارم - «شبکه های عصبی کانولوشنال»
http://muniversity.ir/convolutional-neural-networks/

—---------
محتوای آموزشی شامل کوییز ها- اسلایدها و نوت بوکهای این کورسها
https://t.me/cvision/438


#deep_learning #andrew_ng

#Recommendation

#Andrew_NG strongly recommend for deep learning learners to read a paper which had published on #ArXiv called: " Exploring the Limits of Weakly Supervised Pretraining".

Abstract
State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining. ImageNet classification is the defacto pretraining task for these models. Yet, ImageNet is now nearly ten years old and is by modern standards small. Even so, relatively little is known about the behavior of pretraining with datasets that are multiple orders of magnitude larger. The reasons are obvious: such datasets are difficult to collect and annotate. In this paper, we present a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images. Our experiments demonstrate that training for large-scale hashtag prediction leads to excellent results. We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k single-crop, top-1 accuracy to date: 85.4% (97.6% top-5). We also perform extensive experiments that provide novel empirical data on the relationship between large-scale pretraining and transfer learning performance.

Reference :

https://research.fb.com/publications/exploring-the-limits-of-weakly-supervised-pretraining/
🌿🌿🌿💭💭💭🌹🌹🌹

You can find the paper in the next message.

Your Channel:
https://t.me/Machinelearning_Kartal/1403

#Andrew_NG

شرایط خاص #استخدام در سایت Andrew NG
اگر از اعضای کانال فکر مئ کنند که توانایی های زیر را دارید پس بدونید می توانید شاگرد دانشمند هوش مصنوعی باشید. البته یه جورایی داره راه و رسم هم برای کسانی که دنبال یادگیری ماشین و عمیق هستند را نشون می ده. که خوندش خالی از لطف نیست.


AI is the new electricity. There are millions of opportunities to transform industries with artificial intelligence, but today’s AI job market is broad and undefined. It isn’t always clear to AI engineers - novices and experts alike - how to determine which opportunities best match their career interests and skill sets.
We’re looking for AI engineers of all levels who are seeking new technical roles. We’d like to learn what you’re looking for in your next opportunity, and match you with potential roles available in our affiliated communities. These are applied engineering roles spanning industries including education, manufacturing, health-care, autonomous driving, energy and transportation, robotics, media and entertainment, and more.
Who should apply
If you’re an engineer familiar with machine learning techniques, we’d like to hear from you. That means you’re probably familiar with most of the following:

Deep learning. You should be able to understand and apply major deep learning methods, including neural network training, regularization, optimization methods (gradient descent, Adam), and be familiar with major neural network architecture types such as Convolutional Networks, RNN/LSTM. Completion of the deeplearning.ai specialization is sufficient to meet this criteria.

Machine learning. You should be able to understand and apply major machine learning methods, such as logistic regression, SVM, Decision Trees, Principal Component Analysis and K-means. Completion of Andrew Ng’s Machine Learning course on Coursera is sufficient to meet this criteria.

Implementation. You should have prior experience taking a dataset, cleaning it if necessary, and applying a learning algorithm to it to get a result. You should be able to implement a learning algorithm “from scratch” using a framework such as Tensorflow, Pytorch, Caffe, etc.

General coding. You should be able to code non-trivial functions in object oriented programming, such as popular sorting or search algorithms. You should know how to use your terminal, and work with version control systems (Git). Software engineering experience such as working with relational databases, APIs, and building the back-end of web or mobile applications is helpful but is not required.

Mathematics (including probabilities and statistics.) You should be able to use mathematical notations and linear algebra (matrix/vector operations, dot products, etc.), and understand basic probability theory (distributions, independence, density functions, etc.) as well as statistics (mean, variance, median, quantiles, co-variance, etc.)

منبع:
https://www.deeplearning.ai/careers/

با ما باشید
https://t.me/Machinelearning_Kartal/1436
و به اشتراک بگذارید.

#Andrew_NG

شرایط خاص #استخدام در سایت Andrew NG
اگر از اعضای کانال فکر مئ کنند که توانایی های زیر را دارید پس بدونید می توانید شاگرد دانشمند هوش مصنوعی باشید. البته یه جورایی داره راه و رسم هم برای کسانی که دنبال یادگیری ماشین و عمیق هستند را نشون می ده. که خوندش خالی از لطف نیست.


AI is the new electricity. There are millions of opportunities to transform industries with artificial intelligence, but today’s AI job market is broad and undefined. It isn’t always clear to AI engineers - novices and experts alike - how to determine which opportunities best match their career interests and skill sets.
We’re looking for AI engineers of all levels who are seeking new technical roles. We’d like to learn what you’re looking for in your next opportunity, and match you with potential roles available in our affiliated communities. These are applied engineering roles spanning industries including education, manufacturing, health-care, autonomous driving, energy and transportation, robotics, media and entertainment, and more.
Who should apply
If you’re an engineer familiar with machine learning techniques, we’d like to hear from you. That means you’re probably familiar with most of the following:

Deep learning. You should be able to understand and apply major deep learning methods, including neural network training, regularization, optimization methods (gradient descent, Adam), and be familiar with major neural network architecture types such as Convolutional Networks, RNN/LSTM. Completion of the deeplearning.ai specialization is sufficient to meet this criteria.

Machine learning. You should be able to understand and apply major machine learning methods, such as logistic regression, SVM, Decision Trees, Principal Component Analysis and K-means. Completion of Andrew Ng’s Machine Learning course on Coursera is sufficient to meet this criteria.

Implementation. You should have prior experience taking a dataset, cleaning it if necessary, and applying a learning algorithm to it to get a result. You should be able to implement a learning algorithm “from scratch” using a framework such as Tensorflow, Pytorch, Caffe, etc.

General coding. You should be able to code non-trivial functions in object oriented programming, such as popular sorting or search algorithms. You should know how to use your terminal, and work with version control systems (Git). Software engineering experience such as working with relational databases, APIs, and building the back-end of web or mobile applications is helpful but is not required.

Mathematics (including probabilities and statistics.) You should be able to use mathematical notations and linear algebra (matrix/vector operations, dot products, etc.), and understand basic probability theory (distributions, independence, density functions, etc.) as well as statistics (mean, variance, median, quantiles, co-variance, etc.)

منبع:
https://www.deeplearning.ai/careers/

با ما باشید
https://t.me/Machinelearning_Kartal/1436
و به اشتراک بگذارید.

#fun
#andrew_ng vs #Goodfellow