% 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},
}