% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Neftci:1034463,
      author       = {Neftci, Emre and Jeffrey, Krichmar and Alonso, Nicholas},
      title        = {{U}nderstanding and {I}mproving {O}ptimization in
                      {P}redictive {C}oding {N}etworks},
      publisher    = {arXiv},
      reportid     = {FZJ-2024-07229},
      pages        = {10812-10820},
      year         = {2023},
      abstract     = {Backpropagation (BP), the standard learning algorithm for
                      artificial neural networks, is often considered biologically
                      implausible. In contrast, the standard learning algorithm
                      for predictive coding (PC) models in neuroscience, known as
                      the inference learning algorithm (IL), is a promising,
                      bio-plausible alternative. However, several challenges and
                      questions hinder IL's application to real-world problems.
                      For example, IL is computationally demanding, and without
                      memory-intensive optimizers like Adam, IL may converge to
                      poor local minima. Moreover, although IL can reduce loss
                      more quickly than BP, the reasons for these speedups or
                      their robustness remains unclear. In this paper, we tackle
                      these challenges by 1) altering the standard implementation
                      of PC circuits to substantially reduce computation, 2)
                      developing a novel optimizer that improves the convergence
                      of IL without increasing memory usage, and 3) establishing
                      theoretical results that help elucidate the conditions under
                      which IL is sensitive to second and higher-order
                      information.},
      month         = {Feb},
      date          = {2024-02-20},
      organization  = {The Thirty-Eighth AAAI Conference on
                       Artificial Intelligence (AAAI-24),
                       Vancouver (Canada), 20 Feb 2024 - 27
                       Feb 2024},
      keywords     = {Neural and Evolutionary Computing (cs.NE) (Other) / Neurons
                      and Cognition (q-bio.NC) (Other) / FOS: Computer and
                      information sciences (Other) / FOS: Biological sciences
                      (Other)},
      cin          = {PGI-15},
      cid          = {I:(DE-Juel1)PGI-15-20210701},
      pnm          = {5234 - Emerging NC Architectures (POF4-523)},
      pid          = {G:(DE-HGF)POF4-5234},
      typ          = {PUB:(DE-HGF)8},
      doi          = {10.48550/ARXIV.2305.13562},
      url          = {https://juser.fz-juelich.de/record/1034463},
}