Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks

• URL: http://arxiv.org/abs/2604.24637v2
• Date: Wed, 29 Apr 2026 19:39:18 GMT
• Title: Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks
• Abstract summary: Block-sequential continual learning demands that a single model both protect prior solutions and efficiently infer at inference time which prior solution matches the current input without task labels.<n>We present Functional Task Networks (FTN), a parameter-isolation method inspired by structural and dynamical motifs found in the mammalian neocortex.
• Score: 2.9490560350642405
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Block-sequential continual learning demands that a single model both protect prior solutions from catastrophic forgetting and efficiently infer at inference time which prior solution matches the current input without task labels. We present Functional Task Networks (FTN), a parameter-isolation method inspired by structural and dynamical motifs found in the mammalian neocortex. Similar to mixture-of-experts, this method uses a high dimensional, self-organizing binary mask over a large population of small but deep networks, inspired by dendritic models of pyramidal neurons. The mask is produced by a three-stage procedure: (1) gradient descent on a continuous mask identifies task-relevant neurons, (2) a smoothing kernel biases the result toward spatial contiguity, (3) and k-winner-take-all binarizes the resulting group at a fixed capacity budget. Like mixture-of-experts, each neuron is an independent deep network, so disjoint masks give exactly disjoint gradient updates, providing structural guarantees against catastrophic forgetting. This three-stage procedure recovers the sub-network of a previously-trained task in a single gradient step, providing unsupervised task segmentation at inference time. We test it on three continual-learning benchmarks: (1) a synthetic multi-task classification/regression generator, (2) MNIST with shuffled class labels (pure concept shift), and (3) Permuted MNIST (domain shift). On all three, FTN with fine grained smoothing (FTN-Slow) results in nearly zero forgetting. FTN with a large kernel and only 2 iterations of smoothing (FTN-Fast) trades off some retention for increased speed. We show that the spatial organization mechanism reduces the effective mask search from the combinatorial top-k subset problem in O(C(H,K)) to the complexity of a near-linear scan in O(H) over compact cortical neighborhoods, which is parallelized by the gradient-based update.

Related papers

• Rethinking Learning-Based Influence Maximization: Simple Neural Surrogates and Native Discrete Search [5.337915948350182]
  SIMBA is a diffusion-model-agnostic framework pairing a lightweight neural surrogate with direct discrete search.<n>By shifting from complex representation to effective discrete search, SIMBA drastically cuts time-to-solution while achieving superior spread influence and efficiency.
  arXiv  Detail & Related papers  (2026-08-09T01:47:51Z)
• Breaking chains with trees: Deep learning with $\mathcal{O}(\log N)$ parallel time complexity [0.749500254646884]
  We propose Hierarchical Block-Local Learning (HBLL), a framework that decomposes deep neural networks into hierarchically linked blocks trained using local learning objectives.<n>HBLL is the first algorithm that is able to train deep neural networks in $mathcalO(log N)$ parallel time complexity, where $N$ is the number of network layers.<n>We show that HBLL implicitly defines a family of neuralworks corresponding to different hierarchical paths, enabling flexible inference with different effective numbers of layers.
  arXiv  Detail & Related papers  (2026-06-19T14:44:07Z)
• Self-Supervised Learning via Flow-Guided Neural Operator on Time-Series Data [57.85958428020496]
  Flow-Guided Neural Operator (FGNO) is a novel framework combining operator learning with flow matching for SSL training.<n>FGNO learns mappings in functional spaces by using Short-Time Fourier Transform to unify different time resolutions.<n>Unlike prior generative SSL methods that use noisy inputs during inference, we propose using clean inputs for representation extraction while learning representations with noise.
  arXiv  Detail & Related papers  (2026-02-12T18:54:57Z)
• More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing [5.846028298833611]
  Conditionally Overlapping Mixture of ExperTs (COMET) is a general deep learning method that inducing a modular, sparse architecture with an exponential number of overlapping experts.<n>We demonstrate the effectiveness of COMET on a range of tasks, including image classification, language modeling, and regression.
  arXiv  Detail & Related papers  (2024-10-10T14:58:18Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• Deep Convolutional Learning-Aided Detector for Generalized Frequency Division Multiplexing with Index Modulation [0.0]
  The proposed method first pre-processes the received signal by using a zero-forcing (ZF) detector and then uses a neural network consisting of a convolutional neural network (CNN) followed by a fully-connected neural network (FCNN) The FCNN part uses only two fully-connected layers, which can be adapted to yield a trade-off between complexity and bit error rate (BER) performance. It has been demonstrated that the proposed deep convolutional neural network-based detection and demodulation scheme provides better BER performance compared to ZF detector with a reasonable complexity increase.
  arXiv  Detail & Related papers  (2022-02-06T22:18:42Z)
• Consistent Recurrent Neural Networks for 3D Neuron Segmentation [28.105293815657845]
  We present a recurrent network for the 3D reconstruction of neurons that sequentially generates binary masks for every object in an image with consistency. We evaluate our method on three benchmarks for neuron segmentation and achieved state-of-the-art performance on the SN3D challenge.
  arXiv  Detail & Related papers  (2021-02-01T17:54:46Z)
• NOMA in UAV-aided cellular offloading: A machine learning approach [59.32570888309133]
  A novel framework is proposed for cellular offloading with the aid of multiple unmanned aerial vehicles (UAVs) Non-orthogonal multiple access (NOMA) technique is employed at each UAV to further improve the spectrum efficiency of the wireless network. A mutual deep Q-network (MDQN) algorithm is proposed to jointly determine the optimal 3D trajectory and power allocation of UAVs.
  arXiv  Detail & Related papers  (2020-10-18T17:38:48Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)
• MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling [66.01558025094333]
  We propose a two-stage framework, with the first stage to quickly localize the prostate region and the second stage to precisely segment the prostate. We introduce a novel online metric learning module through voxel-wise sampling in the multi-task network. Our method can effectively learn more representative voxel-level features compared with the conventional learning methods with cross-entropy or Dice loss.
  arXiv  Detail & Related papers  (2020-05-15T10:37:02Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.