% 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”.

@ARTICLE{Stewart:1038223,
      author       = {Stewart, Kenneth and Neumeier, Michael and Shrestha, Sumit
                      Bam and Orchard, Garrick and Neftci, Emre},
      title        = {{E}mulating {B}rain-like {R}apid {L}earning in
                      {N}euromorphic {E}dge {C}omputing},
      publisher    = {arXiv},
      reportid     = {FZJ-2025-01259},
      year         = {2024},
      abstract     = {Achieving personalized intelligence at the edge with
                      real-time learning capabilities holds enormous promise in
                      enhancing our daily experiences and helping decision making,
                      planning, and sensing. However, efficient and reliable edge
                      learning remains difficult with current technology due to
                      the lack of personalized data, insufficient hardware
                      capabilities, and inherent challenges posed by online
                      learning. Over time and across multiple developmental
                      stages, the brain has evolved to efficiently incorporate new
                      knowledge by gradually building on previous knowledge. In
                      this work, we emulate the multiple stages of learning with
                      digital neuromorphic technology that simulates the neural
                      and synaptic processes of the brain using two stages of
                      learning. First, a meta-training stage trains the
                      hyperparameters of synaptic plasticity for one-shot learning
                      using a differentiable simulation of the neuromorphic
                      hardware. This meta-training process refines a hardware
                      local three-factor synaptic plasticity rule and its
                      associated hyperparameters to align with the trained task
                      domain. In a subsequent deployment stage, these optimized
                      hyperparameters enable fast, data-efficient, and accurate
                      learning of new classes. We demonstrate our approach using
                      event-driven vision sensor data and the Intel Loihi
                      neuromorphic processor with its plasticity dynamics,
                      achieving real-time one-shot learning of new classes that is
                      vastly improved over transfer learning. Our methodology can
                      be deployed with arbitrary plasticity models and can be
                      applied to situations demanding quick learning and
                      adaptation at the edge, such as navigating unfamiliar
                      environments or learning unexpected categories of data
                      through user engagement.},
      keywords     = {Neural and Evolutionary Computing (cs.NE) (Other) /
                      Artificial Intelligence (cs.AI) (Other) / FOS: Computer and
                      information 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)25},
      doi          = {10.48550/ARXIV.2408.15800},
      url          = {https://juser.fz-juelich.de/record/1038223},
}