banner
ktran.de
Viet Anh Khoa Tran
@ktran.de
130 followers 910 following 8 posts
PhD student on Dendritic Learning/NeuroAI with Willem Wybo, at Emre Neftci's lab (@fz-juelich.de). ktran.de
Posts Media Videos Starter Packs
ktran.de
Viet Anh Khoa Tran @ktran.de · 20d
Our preprint has been accepted at #NeurIPS2025! 🎉

I will be presenting TMCL in just two weeks at the #BernsteinConference. Hope to see some of you there! @bernsteinneuro.bsky.social

Many thanks to my advisor Willem Wybo, and to Emre Neftci for the great support.
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
New #NeuroAI preprint on #ContinualLearning!

Continual learning methods struggle in mostly unsupervised environments with sparse labels (e.g. parents telling their child the object is an 'apple').
We propose that in the cortex, predictive coding of high-level top-down modulations solves this! (1/6)
2 11
Reposted by Viet Anh Khoa Tran
gtavosanis.bsky.social
gtavosanis.bsky.social @gtavosanis.bsky.social · Sep 8
Björn Kampa, Willem Wybo and I have organized an exciting symposium at the upcomig #BernsteinConference:
bernstein-network.de/bernstein-co...
Everything about Dendrites: Check it out!
(SW2025) From molecules to networks: The dendritic processes that shape learning and memory – Bernstein Netzwerk Computational Neuroscience
bernstein-network.de
2 2
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
This is research from the new Dendritic Learning Group at PGI-15 (‪@fz-juelich.de‬).
A huge thanks to my supervisor Willem Wybo and our institute head Emre Neftci!
📄 Preprint: arxiv.org/abs/2505.14125
🚀 Project page: ktran.de/papers/tmcl/

Supported by (@fzj-jsc.bsky.social) and WestAI.
(6/6)
Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning
Biological brains learn continually from a stream of unlabeled data, while integrating specialized information from sparsely labeled examples without compromising their ability to generalize. Meanwhil...
arxiv.org
3
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
This research opens up an exciting possibility: predictive coding as a fundamental cortical learning mechanism, guided by area-specific modulations that act as high-level control over the learning process. (5/6)
1 1
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
Furthermore, we can dynamically adjust the stability-plasticity trade-off by adapting the strength of the modulation invariance term. (4/6)
1 1
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
Key finding: With only 1% labels, our method outperforms comparable continual learning algorithms both on the continual task and when transferred to other tasks.
Therefore, we continually learn generalizable representations, unlike conventional, class-collapsing methods (e.g. Cross-Entropy). (3/6)
1 1
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
Feedforward weights learn via view-invariant self-supervised learning, mimicking predictive coding. Top-down class modulations, informed by new labels, orthogonalize same-class representations. These are then consolidated into the feedforward pathway through modulation invariance. (2/6)
1 4
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
New #NeuroAI preprint on #ContinualLearning!

Continual learning methods struggle in mostly unsupervised environments with sparse labels (e.g. parents telling their child the object is an 'apple').
We propose that in the cortex, predictive coding of high-level top-down modulations solves this! (1/6)
1 2 11
ktran.de
Viet Anh Khoa Tran @ktran.de · Jun 10
Feedforward weights learn via view-invariant self-supervised learning, mimicking predictive coding. Top-down class modulations, informed by new labels, orthogonalize same-class representations. These are then consolidated into the feedforward pathway through modulation invariance. (2/6)