Title: Rebooting AI : building artificial intelligence we can trust / Gary Marcus and Ernest Davis.
#book #AI
@Machine_learn

Title: Rebooting AI : building artificial intelligence we can trust / Gary Marcus and Ernest Davis.
#book #AI
@Machine_learn

BigBiGAN representation learning models

https://arxiv.org/abs/1907.02544 

TF Hub: https://tfhub.dev/s?publisher=deepmind&q=bigbigan

Try them out in a Colab at: https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/bigbigan_with_tf_hub.ipynb

​​📹Artificial caricature

Agents learn to draw simplified (artistic?) portraits via trial and error.

Project website: https://learning-to-paint.github.io
ArXiV: https://arxiv.org/abs/1910.01007

#GAN #CelebA #DL

Deep Learning with keras
#DL #CNN #LSTM #GRU
#FCNN #book
@Machine_learn

Notes by Tess Ferrandez on the Andrew Ng’s Deep learning specialization.

Very nice way to refresh you memory of DL concepts.
#DL #note
@Machine_learn
Credit: Tess Ferrandez, https://www.slideshare.net/TessFerrandez/notes-fr

1: introduction two machine learning
2: Regression (linear and non-linear)
3: Tensorflow introduction
4: Tensorflow computaion graph
5: Tensorflow optimizer and loss function
6: Tensorflow linear and non linear regression
7: logistic regression
8: Tensorflow regression
_______
9: introduction to traditional machine learning
*10: knn and desicion tree
*11: desicion tree and Naive bayes
*12: desicion tree, knn, Naive bayes implementation
*13: k-means
*14: Guassion Mixture Model(GMM)
*15: implementation K-means and GMM
_____________
16: introduction to Artificial Neural Network
17: Multi-level Neural Network
18: Introduction to Convolution Neural Network
19: Tensorflow Multi-level Neural Network
20:Tensorflow CNN
21:CNN image clasaification
22: Cnn text clasaification
23: Recurrent Neural Network(RNN)
24: implementation RNN
25: RNN image Classification
26: RNN text Classification
__________
*optional class

در این دوره که در ۲۶ جلسه برگزار می شود بسیاری از سرفصل های یادگیری ماشین آموزش داده می شوند تمامی الگوریتم ها بغییر از * براساس کتابخانه Tensorflow اموزش داده می شوند. از پیش نیاز های این دوره آشنایی به زبان پایتون می باشد در صورت عدم آشنایی ۵ جلسه به موارد بالا اضافه می شود. این ۵ جلسه حدودا ۱۰ ساعت کد نویسی می باشد. جلسات به صورت آنلاین و از طریق اسکایپ برگزار می شوند. در انتهای جلسات جهت یادگیری بیشتر چند مساله واقعی به همراه کدنویسی و بدون هزینه برگزار می شود. کلاس ها به صورت کاملا خصوصی می باشند.
جهت رزرو وقت کلاس با ایدی تلگرام زیر در ارتباط باشین.

📱 Teleg: @Raminmousa

Unfolding the Structure of a Document using Deep Learning.
#DL #paper
@Machine_learn
https://arxiv.org/abs/1910.03678

Exploring Massively Multilingual, Massive Neural Machine Translation


http://ai.googleblog.com/2019/10/exploring-massively-multilingual.html
#DL #paper
@Machine_learn

article: https://arxiv.org/pdf/1907.05019.pdf

Master open Cv second edition
#book #OpenCV
@Machine_learn

Chollet deeplearning
#DL #book #Python
@Machine_learn

OpenCV By Example
#DL #book #openCV
@Machine_learn

Open-Source Library for Real-Time Metric-Semantic Localization and Mapping

video: https://www.youtube.com/watch?v=-5XxXRABXJs&feature=youtu.be

code: https://github.com/MIT-SPARK/Kimera

article: https://arxiv.org/abs/1910.02490

CrypTen: A new research tool for secure machine learning with PyTorch

https://ai.facebook.com/blog/crypten-a-new-research-tool-for-secure-machine-learning-with-pytorch


code: https://github.com/facebookresearch/CrypTen

ICCV 2019 papers open access

http://openaccess.thecvf.com/ICCV2019.py

Workshops:


http://openaccess.thecvf.com/ICCV2019_workshops/menu.py

Neural networks in NLP are vulnerable to adversarially crafted inputs.

We show that they can be trained to become certifiably robust against input perturbations such as typos and synonym substitution in text classification:

https://arxiv.org/abs/1909.01492

2019 #Deep_Learning Based Recommender System A #Survey and New Perspectives
@Machine_learn

Deep learning for biometrics
#book #Dl
@Machine_learn