Model for material elasticity and plasticity using networks.
problem Understanding the elasticity and plasticity of materials.
method Developed a mathematical model based on networks, defining tension tensor for periodic graphs.
result The model explains elasticity and plasticity through local moves on graphs.
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just li…
Natural gradient learning improves synaptic plasticity in spiking neurons.
problem Parametrization dependence leads to inconsistencies in classical synaptic plasticity theories.
method Proposes natural gradient descent in Riemannian geometry for spiking neurons.
result Derives a synaptic learning rule that explains biological phenomena.
Learning and memory in the brain are implemented by complex, time-varying changes in neural circuitry. The computational rules according to which synaptic weights change over time are the subject of much research, and are not precisely understood. Until recently, limitations in experimental methods have made it challen…
Proposes a plastic neural memory model for better anomaly detection.
problem Static attention mechanisms limit NMNs in anomaly detection.
method Introduces dynamic connection weights for improved knowledge retrieval.
result Outperforms state-of-the-art in three medical anomaly detection tasks.
Multi-model forgetting occurs when training multiple deep networks sequentially, leading to performance degradation of previously trained models.
problem Performance degradation of previously trained models when sequentially training multiple deep networks with shared parameters.
method Introduce a weight plasticity loss that regularizes the learning of shared parameters based on their importance for previous models.
result Weight plasticity loss effectively preserves the performance of previously trained models during sequential training and neural architecture search.
AANets balance stability and plasticity in CIL.
problem Stability-plasticity dilemma in class-incremental learning.
method Adaptive Aggregation Networks (AANets) with stable and plastic residual blocks.
result AANets improve performance on CIL benchmarks.
Sleep-based regularization stabilizes STDP in recurrent neural networks.
problem Pathological weight dynamics in recurrent SNNs.
method Periodic offline phases with stochastic decay and spontaneous activity.
result Sleep-based renormalization prevents weight saturation and preserves learned structure.
Oja's rule improves neural network training without engineered tricks.
problem Training deep neural networks with biological constraints.
method Incorporating Oja's plasticity rule into error-driven training.
result Stable, efficient learning in feedforward and recurrent architectures.
A model retains learned knowledge for longer by adding a plastic component to neural networks.
problem Catastrophic forgetting in neural networks when learning new tasks.
method Differentiable Hebbian Consolidation model with a DHP Softmax layer.
result Reduces forgetting in benchmarks like Permuted MNIST and Vision Datasets Mixture.
This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to the…
New method improves deep learning performance without weight symmetry.
problem Challenges in scaling non-symmetric learning methods to deep convolutional networks.
method Introduced techniques to mitigate scalability issues, including a modified feedback alignment method.
result Demonstrated competitive performance with backpropagation using a weaker form of weight symmetry.
Proposes a method to prevent neural networks from forgetting learned tasks.
problem Catastrophic forgetting in neural networks.
method Attention-based selective plasticity of synapses inspired by the cholinergic neuromodulatory system.
result Competitive performance on benchmark tasks compared to state-of-the-art methods.
Introduces generalized almost plastic structures on manifolds.
problem Integrability of plastic structures on manifolds.
method Constructs a family of generalized almost plastic structures on pseudo-Riemannian manifolds with specific tensor fields and compatibility conditions.
result Characterizes the integrability of these structures with respect to a given affine connection.
Model neural plasticity as binary optimization to dynamically activate or deactivate network units.
problem Dynamic learning and adaptability of neural networks.
method Model neural plasticity as an L0-norm regularized binary optimization problem, where units can be activated or deactivated based on a cost-benefit tradeoff. result Demonstrates that a single parameter k can modulate learning dynamics, unifying network sparsification and expansion. Study evaluates CL methods in RNNs, highlighting differences from feedforward networks.
problem Preventing catastrophic forgetting in RNNs processing sequential data.
method Comprehensive evaluation of CL methods, including elastic weight consolidation and hypernetworks.
result Weight-importance methods perform similarly regardless of sequence length but require more stability for high working memory demands.
Improved neural ODEs learn adaptable flows.
problem Neural ODEs struggle with expressive power and adaptability.
method Introduce N-CODE modules with dynamic parameters controlled by a trainable map.
result N-CODE modules enhance expressivity of neural ODEs.
Flashback Learning balances model stability and plasticity in continual learning.
problem Balancing model stability and plasticity in continual learning.
method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.
result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.
Physics-informed deep learning approximates strain gradient plasticity solutions.
problem Stiffness and computational challenges in solving strain gradient plasticity models.
method Physics-informed deep learning (PIDL) with modified loss functions and optimization schemes.
result PIDL methods address stiffness and computational challenges in strain gradient plasticity.
We propose a particularly structured Boltzmann machine, which we refer to as a dynamic Boltzmann machine (DyBM), as a stochastic model of a multi-dimensional time-series. The DyBM can have infinitely many layers of units but allows exact and efficient inference and learning when its parameters have a proposed structure…
Biological neurons learn tensor decompositions of higher-order correlations using nonlinear Hebbian plasticity.
problem Learning higher-order correlations in biological neurons.
method Introduce and study generalized nonlinear Hebbian learning rules.
result Neurons can learn tensor eigenvectors of higher-order input correlation tensors.
Unified approach for neural networks with multi-compartmental neurons and non-Hebbian plasticity.
problem Limited computational power of existing neural network models for multi-compartmental neurons and non-Hebbian plasticity.
method Unified extension of similarity matching approach to derive neural networks with multi-compartmental neurons and local, non-Hebbian learning rules.
result Unified approach facilitates understanding of multi-compartmental neuronal structures and non-Hebbian plasticity.
Vision transformers benefit from non-smooth components in adaptation.
problem Understanding the role of non-smoothness in vision transformer adaptation.
method Theoretical analysis and extensive experiments on large-scale vision transformers.
result High plasticity of attention modules and feedforward layers leads to better finetuning performance.
Metric anomalies arising from a distribution of point defects (intrinsic interstitials, vacancies, point stacking faults), thermal deformation, biological growth, etc. are well known sources of material inhomogeneity and internal stress. By emphasizing the geometric nature of such anomalies we seek their representation…
Unified framework for strain-gradient plasticity from dislocations.
problem Deriving strain-gradient plasticity from edge-dislocations.
method Γ-limit derivation in a continuum framework with smooth frame fields and dislocation circulation.
result Unified strain-gradient model with new geometric rigidity estimates.
Selective reinitialization improves adaptability of neural bandits in dynamic environments.
problem Loss of plasticity in neural bandits, leading to rigid neural network parameters.
method Selective Reinitialization (SeRe) framework that dynamically resets underutilized units.
result SeRe enhances adaptability of CNB algorithms, reducing cumulative regret in dynamic environments.
This paper presents a method to improve continual learning stability and plasticity.
problem Balancing learning stability and plasticity in deep learning.
method Batch-level Experience Replay with Review approach.
result Achieved 1st place in all three scenarios of the CVPR 2020 CLVision challenge.
VSML unifies meta learning concepts and enables simple backpropagation.
problem Improving and unifying meta learning concepts for neural networks.
method Unified approach using variable shared meta learning and simple weight-sharing.
result Simple backpropagation can be implemented and meta learned without gradient calculation.
Elite ONNs learn better with synaptic plasticity, improving performance over CNNs.
problem Limited heterogeneity in ONNs due to fixed operator sets.
method Synaptic plasticity-based search for optimal operator sets.
result Elite ONNs achieve superior learning performance compared to conventional methods.
Dropout helps a stable network learn new tasks without forgetting old ones.
problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Investigate the relationship between dropout and stability in neural networks, showing dropout acts as an implicit gating mechanism.
result Dropout stabilizes a network's learning, allowing it to learn new tasks without forgetting old ones.
Learning weights in a spiking neural network with hidden neurons, using local, stable and online rules, to control non-linear body dynamics is an open problem. Here, we employ a supervised scheme, Feedback-based Online Local Learning Of Weights (FOLLOW), to train a network of heterogeneous spiking neurons with hidden l…
New insights into continual learning with task similarity.
problem Challenges in learning similar tasks without interference.
method Linear teacher-student model with latent structure.
result High input feature similarity with low readout similarity is catastrophic.
A brain-inspired spiking Transformer reduces energy consumption and enhances interpretability.
problem Energy inefficiency and lack of interpretability in Transformer models.
method Spiking STDP Transformer using spike-timing-dependent plasticity (STDP) for self-attention.
result Achieves 94.35% and 78.08% accuracy on CIFAR-10 and CIFAR-100 datasets respectively, with 88.47% energy reduction.
A neuromemristive HTM architecture boosts robustness and performance.
problem Improving robustness and performance of HTM algorithms.
method Developed a neuromemristive crossbar architecture for HTM, incorporating memristors and neurogenesis.
result Enhanced robustness and performance of HTM through neuromemristive architecture.
Analyze and predict complex 3D shape deformations using LSTM autoencoders and oriented bounding boxes.
problem Detecting and predicting patterns in sequences of deforming 3D shapes.
method Use LSTM autoencoders to create low-dimensional representations of 3D shapes, incorporating oriented bounding boxes for structural components.
result The method detects patterns in plastic deformation and predicts future states of 3D shapes with improved accuracy.
The quest for biologically plausible deep learning is driven, not just by the desire to explain experimentally-observed properties of biological neural networks, but also by the hope of discovering more efficient methods for training artificial networks. In this paper, we propose a new algorithm named Variational Proba…
Bio-inspired neural networks use predictive coding for efficient weight updates.
problem Training artificial neural networks efficiently and biologically plausibly.
method Predictive Coding (PC) updates weights locally using only local information.
result PC provides theoretical advantages like automatic gradient scaling.
EILearn learns incrementally using previous classifier knowledge.
problem Incremental learning with previous data.
method Retains and uses previous classifier knowledge, monitors performance, eliminates poorly performing classifiers.
result Outperforms existing incremental learning approaches.
Olshausen and Field (OF) proposed that neural computations in the primary visual cortex (V1) can be partially modeled by sparse dictionary learning. By minimizing the regularized representation error they derived an online algorithm, which learns Gabor-filter receptive fields from a natural image ensemble in agreement …
Identifies learning rules from neural network observables.
problem Determine the underlying plasticity rules governing learning in biological systems.
method Simulated idealized neuroscience experiments with artificial neural networks to generate a dataset of learning trajectories. Used linear and non-linear classifiers to identify learning rules from aggregate statistics of weights, activations, and activity changes.
result Different classes of learning rules can be separated solely on the basis of aggregate statistics of the weights, activations, or instantaneous layer-wise activity changes.
Proposes a new neural network approach to credit assignment.
problem Credit assignment problem in deep neural networks.
method Contrastive similarity matching objective function.
result Deep networks learn to match similarity between layers.
Despite our extensive knowledge of biophysical properties of neurons, there is no commonly accepted algorithmic theory of neuronal function. Here we explore the hypothesis that single-layer neuronal networks perform online symmetric nonnegative matrix factorization (SNMF) of the similarity matrix of the streamed data. …
A new learning framework mimics biological STDP for neural networks.
problem To create a neural network that learns like biological systems.
method Developed MSTDP framework using Spike-timing dependent plasticity rules.
result Framework can learn and generate patterns without additional supervision.
A high-parallelism SNN improves feature learning efficiency and robustness.
problem Slow learning speed and limited learning capability in existing SNNs.
method Inspired by Inception modules, high-parallelism architecture, Vote-for-All decoding, adaptive repolarization mechanism.
result Superior performance and competitive accuracy compared to state-of-the-art unsupervised SNNs.
UCL uses uncertainty to improve continual learning without extra memory.
problem Memory and performance issues in continual learning.
method Adapts Bayesian online learning with variational inference, introducing node-wise uncertainty and stability terms.
result UCL outperforms state-of-the-art methods on supervised and reinforcement learning tasks.
A dynamic Boltzmann machine (DyBM) has been proposed as a model of a spiking neural network, and its learning rule of maximizing the log-likelihood of given time-series has been shown to exhibit key properties of spike-timing dependent plasticity (STDP), which had been postulated and experimentally confirmed in the fie…
Current studies about motor imagery based rehabilitation training systems for stroke subjects lack an appropriate analytic method, which can achieve a considerable classification accuracy, at the same time detects gradual changes of imagery patterns during rehabilitation process and disinters potential mechanisms about…
LoRA- improves EFCL by stabilizing feature drifts.
problem Catastrophic forgetting in exemplar-free continual learning.
method LoRA-subtraction to adaptively subtract old task weights.
result LoRA- achieves state-of-the-art performance in EFCL.