= Felix A. Gers
{c}
<Felix A. Gers> is a researcher in <machine learning> and <recurrent neural networks>. His institutional profile connects his research with <long short-term memory>; the full-name byline of his2000paper verifies the name used here.<Felix Gers profile by BHT>[Research biography and IDSIA collaboration]{ref} <Learning to Forget: Continual Prediction with LSTM by Felix A. Gers, Jürgen Schmidhuber and Fred Cummins>[MIT Press full author byline; DOI10.1162/089976600300015015]{ref}
With <Jürgen Schmidhuber> and <Fred Cummins>, he introduced the adaptive <LSTM forget gate> to address continual input streams lacking externally marked reset points. The gate lets a <LSTM memory cell> learn when to reduce retained state, rather than requiring every sequence boundary to be supplied from outside.<Learning to Forget: Continual Prediction with LSTM by Felix A. Gers, Jürgen Schmidhuber and Fred Cummins>[Abstract: continual prediction and learned resets]{ref}
A scalar toy update makes selective retention tangible:
$$
c_t=f_tc_{t-1}+u_t.
$$
Here $f_t$ is a retention multiplier and $u_t$ a new contribution. With $c_{t-1}=8$ and $u_t=0$, choices $f_t=1$, $0.25$ and $0$ retain $8$, $2$ and $0$ respectively. This arithmetic illustrates one role of a <LSTM forget gate>; it omits the other gates and training equations of a complete <long short-term memory> network. Forgetting stored state is also distinct from discarding all learned network parameters.
\Image[https://foundationmodels.bht-berlin.de/assets/uploads/2026/04/Felix-Gers.jpg]
{title=Felix Gers, identified on his BHT research profile}
{description=External institutional portrait from <Felix Gers profile by BHT>.}
Back to article page
