% 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{Tran:1025142,
      author       = {Tran, Viet Anh Khoa and Neftci, Emre and Wybo, Willem},
      title        = {{C}ontinual learning using dendritic modulations on
                      view-invariant feedforward weights},
      reportid     = {FZJ-2024-02719},
      year         = {2024},
      abstract     = {The brain is remarkably adept at learning from a continuous
                      stream of data without significantlyforgetting previously
                      learnt skills. Conventional machine learning models struggle
                      at continual learn-ing, as weight updates that optimize the
                      current task interfere with previously learnt tasks. A
                      simpleremedy to catastrophic forgetting is freezing a
                      network pretrained on a set of base tasks, and
                      trainingtask-specific readouts on this shared trunk.
                      However, this assumes that representations in the
                      frozennetwork are separable under new tasks, therefore
                      leading to sub-par performance. To continually learnon novel
                      task data, previous methods suggest weight consolidation –
                      preserving weights that are mostimpactful for the
                      performance of previous tasks – and memory-based
                      approaches – where the networkis allowed to see a subset
                      of images from previous tasks.For biological networks, prior
                      work showed that dendritic top-down modulations provide a
                      powerfulmechanism to learn novel tasks while initial
                      feedforward weights solely extract generic
                      view-invariantfeatures. Therefore, we propose a continual
                      learner that optimizes the feedforward weights
                      towardsview-invariant representations while training
                      task-specific modulations towards separable class clus-ters.
                      In a task-incremental setting, we train feedforward weights
                      using a self-supervised algorithm,while training the
                      task-specific modulations and readouts in a supervised
                      fashion, both exclusivelythrough current-task data. We show
                      that this simple approach avoids catastrophic forgetting of
                      classclusters, as opposed to training the whole network in a
                      supervised manner, while also outperforming(a) task-specific
                      readout without modulations and (b) frozen feedforward
                      weights. This suggests that(a) top-down modulations are
                      necessary and sufficient to shift the representations
                      towards separableclusters and that (b) the SSL objective
                      learns novel features based on the newly presented
                      objectswhile maintaining features relevant to previous
                      tasks, without requiring specific synaptic
                      consolidationmechanisms.},
      month         = {Feb},
      date          = {2024-02-29},
      organization  = {Computational and Systems Neuroscience
                       2024, Lisbon (Portugal), 29 Feb 2024 -
                       3 Mar 2024},
      subtyp        = {After Call},
      cin          = {PGI-15},
      cid          = {I:(DE-Juel1)PGI-15-20210701},
      pnm          = {5234 - Emerging NC Architectures (POF4-523) / Functional
                      Neural Architectures $(jinm60_20190501)$ / WestAI - AI
                      Service Center West (01IS22094B)},
      pid          = {G:(DE-HGF)POF4-5234 / $G:(DE-Juel1)jinm60_20190501$ /
                      G:(BMBF)01IS22094B},
      typ          = {PUB:(DE-HGF)24},
      doi          = {10.34734/FZJ-2024-02719},
      url          = {https://juser.fz-juelich.de/record/1025142},
}