Understanding LSTM Networks -- colah's blog

Humans don’t start their thinking from scratch every second. As you read this essay, you understand each word based on your understanding of previous words. You don’t throw everything away and start thinking from scratch again. Your thoughts have persistence.

Understanding LSTM Networks -- colah's blog Understanding LSTM Networks Posted on August 27, 2015 Recurrent Neural Networks Humans don’t start their thinking from scratch every second. As you read this essay, you understand each word based on your understanding of previous words. You don’t throw everything away and start thinking from scratch again. Your thoughts have persistence. Traditional neural networks can’t do this, and it seems like a major shortcoming. For example, imagine you want to classify what kind of event is happening at every point in a movie. It’s unclear how a traditional ne

saved by

• Marco Jiralerspong
• Claire Wang
• Fernando Silva
• Atem Aguer
• Sarah Pan
• Jianmin Chen
• Lydia Nottingham
• Vivek Shukla
• Rohan Kanti
• Uday S

related reading

• The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
• Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs · Denny's Blogdennybritz.com
• Ilya 30u30arc.net
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• Long short-term memory - Wikipediaen.wikipedia.org
• Recurrent neural networks - Scholarpediascholarpedia.org
• [2501.00663] Titans: Learning to Memorize at Test Timearxiv.org
• An Overview of Deep Learning for Curious People | Lil'Loglilianweng.github.io
• The Decade of Deep Learning | Leo Gaobmk.sh
• https://aclanthology.org/P19-1285.pdfaclanthology.org
• Recurrent neural network - Wikipediaen.wikipedia.org
• The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io