Machine Learning
Machine Learning - - AI - - Data Science
*Free Paid Books
*Video Courses
*Research Papers
*Codes
*Projects
*Development
*Tricks and Hacks
*Pythonic stuff
https://t.me/machinelearninglovers
Machine Learning - - AI - - Data Science
*Free Paid Books
*Video Courses
*Research Papers
*Codes
*Projects
*Development
*Tricks and Hacks
*Pythonic stuff
https://t.me/machinelearninglovers
Telegram
Machine Learning
Machine Learning - - AI - - Data Science
*Free Paid Books
*Video Courses
*Research Papers
*Codes
*Projects
*Development
*Tricks and Hacks
*Pythonic stuff
*Free Paid Books
*Video Courses
*Research Papers
*Codes
*Projects
*Development
*Tricks and Hacks
*Pythonic stuff
That's the invite link of our telegram channel. Share the invite link in your coding group, DS group, friends circle nd help them to join nd learn with us.
New Deep Learning Baseline for Image Classification called FrequentNet just got released!
Paper: https://arxiv.org/pdf/2001.01034.pdf
Paper: https://arxiv.org/pdf/2001.01034.pdf
Hey MLL we know that Day 29 & Day 30 Interview Preparation material is left to be uploaded. Apologise for delays but we are constantly putting our efforts on thinking how to provide enough value to your preparations with this last 2 notes. But now we are almost done with it. Notes will get uploaded by tonight. 💯
And for your acknowledgement something amazing is coming after the end of Interview Preparation Questions.
Uber AI Plug and Play Language Model (PPLM)
PPLM allows a user to flexibly plug in one or more simple attribute models representing the desired control objective into a large, unconditional language modeling (LM). The method has the key property that it uses the LM as is – no training or fine-tuning is required – which enables researchers to leverage best-in-class LMs even if they don't have the extensive hardware required to train them.
PPLM lets users combine small attribute models with an LM to steer its generation. Attribute models can be 100k times smaller than the LM and still be effective in steering it
PPLM algorithm entails three simple steps to generate a sample:
* given a partially generated sentence, compute log(p(x)) and log(p(a|x)) and the gradients of each with respect to the hidden representation of the underlying language model. These quantities are both available using an efficient forward and backward pass of both models;
* use the gradients to move the hidden representation of the language model a small step in the direction of increasing log(p(a|x)) and increasing log(p(x));
* sample the next word
more at paper: https://arxiv.org/abs/1912.02164
blogpost: https://eng.uber.com/pplm/
code: https://github.com/uber-research/PPLM
online demo: https://transformer.huggingface.co/model/pplm
#nlp #lm #languagemodeling #uber #pplm
PPLM allows a user to flexibly plug in one or more simple attribute models representing the desired control objective into a large, unconditional language modeling (LM). The method has the key property that it uses the LM as is – no training or fine-tuning is required – which enables researchers to leverage best-in-class LMs even if they don't have the extensive hardware required to train them.
PPLM lets users combine small attribute models with an LM to steer its generation. Attribute models can be 100k times smaller than the LM and still be effective in steering it
PPLM algorithm entails three simple steps to generate a sample:
* given a partially generated sentence, compute log(p(x)) and log(p(a|x)) and the gradients of each with respect to the hidden representation of the underlying language model. These quantities are both available using an efficient forward and backward pass of both models;
* use the gradients to move the hidden representation of the language model a small step in the direction of increasing log(p(a|x)) and increasing log(p(x));
* sample the next word
more at paper: https://arxiv.org/abs/1912.02164
blogpost: https://eng.uber.com/pplm/
code: https://github.com/uber-research/PPLM
online demo: https://transformer.huggingface.co/model/pplm
#nlp #lm #languagemodeling #uber #pplm