Neha Pawar

41 posts

Neha Pawar

Neha Pawar

@traintestrepeat

NLP Enthusiast, Applied Research, Datascientist @DATEV

Nuremberg, Bavaria Inscrit le Haziran 2019
139 Abonnements19 Abonnés
Neha Pawar retweeté
Google AI
Google AI@GoogleAI·
Stop by the #ICLR2024 Google booth today at 3:15 PM to hear @rach_it_ and @nitish_gup talk about Composition to Augment Language Models (CALM), which introduce cross-attention between LLMs to compose their representations and enable new capabilities.
Google AI tweet media
English
4
104
393
66.6K
Neha Pawar
Neha Pawar@traintestrepeat·
@zehavoc @mayhewsw Except that express in some parts of the world mean <90km/hr . Highlights the need to have an uniform understanding where the LLMs begin?
English
0
0
0
45
Djamé..
Djamé..@zehavoc·
@traintestrepeat @mayhewsw it's like keeping calling "express" some old train lines with trains that don't go faster than 90 km/h. We all contextualize :)
English
1
0
0
87
Stephen Mayhew
Stephen Mayhew@mayhewsw·
is BERT an LLM? at the time, 340M params seemed like a lot, but that's more than 500x smaller than GPT3.
English
18
3
47
22.6K
Neha Pawar
Neha Pawar@traintestrepeat·
@IamSubhayu Subhayu, it breaks my heart to read the trouble you are going through. As a fellow NRI, I can relate to what you are feeling. I am hoping the tough times are over soon.
English
0
0
1
0
Neha Pawar
Neha Pawar@traintestrepeat·
@ChristianKlose3 The lottery ticket hypothesis is impressive. It was also my Tweet debut ;)
English
0
0
1
0
Neha Pawar retweeté
François Chollet
François Chollet@fchollet·
There are two kinds of software developers: those who already use deep learning, and those who will use deep learning next.
English
17
84
715
0
Neha Pawar retweeté
Ferenc Huszár
Ferenc Huszár@fhuszar·
Perserverance, you're on mute.
English
1
4
49
0
Neha Pawar
Neha Pawar@traintestrepeat·
@DhirajS65167098 Famous and the one that works may not the same. In NLP, there is also no one shoe that fits all. I follow the following steps: understand the usecase, read on the concepts that work for the problem, experiment and build an intuition for the various problems. I hope this helps
English
0
0
0
0
Dhiraj Sharma
Dhiraj Sharma@IamDhirajShama·
@traintestrepeat Hi Thank you so much for your reply, I will keep trying to be up to date. Do you have any famous algorithm which I should focus the most?
English
2
0
0
0
Dhiraj Sharma
Dhiraj Sharma@IamDhirajShama·
@traintestrepeat Hello Neha, I hope you are doing well? I am also mad about NLP analysis and everything about NLP but I am lost between NLTK, SpaCy & Gensim, could you please guide me where should I focus the most and what would a great project for NLP. Thanks a lot
English
1
1
0
0
Neha Pawar
Neha Pawar@traintestrepeat·
@DhirajS65167098 Famous and the one that works for may not the same. In NLP, there is also no one shoe that fits all. I follow the following steps: understand the usecase, read on the concepts that work for the problem, experiment and build an intuition for the various problems. I hope this helps
English
1
0
1
0
Neha Pawar
Neha Pawar@traintestrepeat·
@DhirajS65167098 When you hit a wall or want a solution more specific to your usecase you will feel the need to learn tensorflow or pytorch. n/n
English
1
0
2
0
Neha Pawar
Neha Pawar@traintestrepeat·
@DhirajS65167098 If you're at early stages, it can be sometimes frustrating. But, persevere and I promise it gets better. The library you use will heavily depend on your usecase. I would advice you to start off with a high level library for rapid prototyping. Spacy is a good choice. 2/n
English
1
0
1
0
Neha Pawar
Neha Pawar@traintestrepeat·
@elonmusk suggests Signal (the app) as an alternative for whatsapp and stocks spike up for an unrelated company called Signal > 0.6 to 7$ right now. Pure fun for anyone trying to perfect the stock prediction algorithm :D
K10✨@Kristennetten

@elonmusk @elonmusk this poor company has just been launched from .60 a share to 3.60 + due to people thinking you meant Signal the Company $SIGL & not the social app. 😅

English
0
0
0
0