MIT 6.8210: Underactuated Robotics
Spring 2023, Lecture 2
Follow live at https://slides.com/d/FSRCIMY/live
(or later at https://slides.com/russtedrake/spring23-lec02)
https://en.wikipedia.org/wiki/Long_short-term_memory
“RNNs using LSTM units partially solve the vanishing gradient problem, because LSTM units allow gradients to also flow unchanged.”
\(x_i\) represents activation (e.g. firing rate) of neuron \(i\).
"Memory" is fixed point.
Dynamics can fill in the details.
from Hertz, Krogh, Palmer, 1991.
By russtedrake
MIT Underactuated Robotics Spring 2023 http://underactuated.csail.mit.edu
Roboticist at MIT and TRI