A joint institute for AI research
Founded in Lugano in 1988 by Angelo Dalle Molle, IDSIA combines AI research and teaching. Its overview describes a joint USI/SUPSI bridge affiliation since 2000, with work spanning neural networks, probabilistic and causal models, robotics, control and optimization. That joint structure does not justify assigning it to one sole parent. [1]
Its neural-network research includes recurrent systems for sequence processing and long-range dependencies. The 1997 LSTM paper by Sepp Hochreiter and Jürgen Schmidhuber describes a gated architecture intended to preserve error signals across long intervals. The bibliographic record identifies Hochreiter's TUM affiliation, so the paper should not be represented as exclusively developed at IDSIA. [2][3]
LSTM addresses learning dependencies across sequences. IDSIA's present research remit extends beyond that historical paper to reinforcement learning, geometric deep learning and causal reasoning. [3][1]