This is curated collection of free places where you can learn about deep-learning. If you've always wanted to learn about deep-learning but don't know where to start, you might have stumbled upon the right place!
https://mithi.github.io/deep-blueberry/ch0-introduction.html
https://mithi.github.io/deep-blueberry/ch0-introduction.html
Deep Learning for Sentiment Analysis: A Survey
https://arxiv.org/ftp/arxiv/papers/1801/1801.07883.pdf
Sentiment Analysis Benchmark Datasets & State of the art papers:
https://github.com/sebastianruder/NLP-progress/blob/master/english/sentiment_analysis.md
https://arxiv.org/ftp/arxiv/papers/1801/1801.07883.pdf
Sentiment Analysis Benchmark Datasets & State of the art papers:
https://github.com/sebastianruder/NLP-progress/blob/master/english/sentiment_analysis.md
GitHub
NLP-progress/sentiment_analysis.md at master · sebastianruder/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks. - NLP-progress/sentiment_analysis.md at...
Forwarded from The Devs
Forwarded from School of AI
zisserman-self-supervised.pdf
9.1 MB
A tutorial on Self-supervised Learning by Andrew Zisserman from Google Deep Mind.
Talks in ICML2019:
https://www.facebook.com/icml.imls/videos/2030095370631729/
Talks in ICML2019:
https://www.facebook.com/icml.imls/videos/2030095370631729/
An overview of old and new nlp pretrained models use-cases (Excluding XLNet):
https://www.youtube.com/watch?v=0EtD5ybnh_s
#NLP
https://www.youtube.com/watch?v=0EtD5ybnh_s
#NLP
YouTube
Language Learning with BERT - TensorFlow and Deep Learning Singapore
Speaker: Martin Andrews
Event Page: https://www.meetup.com/TensorFlow-and-Deep-Learning-Singapore/events/256431012/
Produced by Engineers.SG
Help us caption & translate this video!
https://amara.org/v/mToR/
Event Page: https://www.meetup.com/TensorFlow-and-Deep-Learning-Singapore/events/256431012/
Produced by Engineers.SG
Help us caption & translate this video!
https://amara.org/v/mToR/
Empirically, XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment analysis, and document ranking.
https://arxiv.org/abs/1906.08237#
#NLP
https://arxiv.org/abs/1906.08237#
#NLP
arXiv.org
XLNet: Generalized Autoregressive Pretraining for Language Understanding
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language...
A great introduction to Multivariate Gaussian Distributations:
https://www.youtube.com/watch?v=eho8xH3E6mE
#statistics
https://www.youtube.com/watch?v=eho8xH3E6mE
#statistics
YouTube
Multivariate Gaussian distributions
Properties of the multivariate Gaussian probability distribution
A great introduction to Multivariate Gaussian Distributations:
https://www.youtube.com/watch?v=JNlEIEwe-Cg
#statistics
https://www.youtube.com/watch?v=JNlEIEwe-Cg
#statistics
YouTube
Gaussian Mixture Models - The Math of Intelligence (Week 7)
We're going to predict customer churn using a clustering technique called the Gaussian Mixture Model! This is a probability distribution that consists of multiple Gaussian distributions, very cool. I also have something important but unrelated to say in the…
Forwarded from Machine learning books and papers (Ramin Mousa)
Adapters: A Compact and Extensible Transfer Learning Method for NLP
____
@Machine_learn
___
https://medium.com/dair-ai/adapters-a-compact-and-extensible-transfer-learning-method-for-nlp-6d18c2399f62
____
@Machine_learn
___
https://medium.com/dair-ai/adapters-a-compact-and-extensible-transfer-learning-method-for-nlp-6d18c2399f62
Medium
Adapters: A Compact and Extensible Transfer Learning Method for NLP
Adapters obtain comparable results to BERT on several NLP tasks while achieving parameter efficiency.
Forwarded from School of AI
Neural Code Search: ML-based code search using natural language queries:
https://ai.facebook.com/blog/neural-code-search-ml-based-code-search-using-natural-language-queries/
https://ai.facebook.com/blog/neural-code-search-ml-based-code-search-using-natural-language-queries/
Facebook
Neural Code Search: ML-based code search using natural language queries
We’ve developed an internal tool that applies natural language processing and information retrieval techniques directly to source code text, in order to produce an machine learning-based code search system.
A great tutorial which shows you how you can implement algorithms above, in Python:
https://github.com/MorvanZhou/Evolutionary-Algorithm
https://github.com/MorvanZhou/Evolutionary-Algorithm
Deep unsupervised Learning Course by Google:
https://sites.google.com/view/berkeley-cs294-158-sp19/home
https://sites.google.com/view/berkeley-cs294-158-sp19/home
Google
CS294-158-SP19 Deep Unsupervised Learning Spring 2019
About: This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-supervised Learning. Recent advances in generative models have made it possible to realistically model high-dimensional raw data…
Forwarded from Tensorflow(@CVision) (Vahid Reza Khazaie)
New Google Brain Optimizer Reduces BERT Pre-Training Time From Days to Minutes
کاهش مدت زمان pre-training مدل زبانی BERT از سه روز به 76 دقیقه با ارائه یک تابع بهینه ساز جدید!
Google Brain researchers have proposed LAMB (Layer-wise Adaptive Moments optimizer for Batch training), a new optimizer which reduces training time for its NLP training model BERT (Bidirectional Encoder Representations from Transformers) from three days to just 76 minutes.
لینک مقاله: https://arxiv.org/abs/1904.00962
لینک بلاگ پست: https://medium.com/syncedreview/new-google-brain-optimizer-reduces-bert-pre-training-time-from-days-to-minutes-b454e54eda1d
#BERT #language_model #optimizer
کاهش مدت زمان pre-training مدل زبانی BERT از سه روز به 76 دقیقه با ارائه یک تابع بهینه ساز جدید!
Google Brain researchers have proposed LAMB (Layer-wise Adaptive Moments optimizer for Batch training), a new optimizer which reduces training time for its NLP training model BERT (Bidirectional Encoder Representations from Transformers) from three days to just 76 minutes.
لینک مقاله: https://arxiv.org/abs/1904.00962
لینک بلاگ پست: https://medium.com/syncedreview/new-google-brain-optimizer-reduces-bert-pre-training-time-from-days-to-minutes-b454e54eda1d
#BERT #language_model #optimizer
arXiv.org
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization methods to tackle...