Inspiration Learning expands imitation learning to different action spaces.
problem Current imitation learning techniques are limited to agents with the same action space.
method Designs Advantage Actor-Critic algorithms using Preferential based Reinforcement Learning.
result Method extends imitation learning to new action spaces.
CHANI learns classification tasks with local transformations inspired by biology.
problem Proving neural networks can learn classification tasks with local transformations.
method CHANI uses spiking neurons modeled by Hawkes processes with expert aggregation for local learning.
result CHANI can learn and encode multiple classes, forming assemblies of neurons.
The study explores how brain development can inspire efficient deep learning models.
problem Efficient and robust optimization procedures for deep learning.
method Inspiration from biological neural development to improve deep learning models.
result Biological neural development can inspire efficient and robust optimization procedures.
New deep learning models inspired by fuzzy logic are more robust to adversarial attacks.
problem Flawed generalization in deep neural networks leading to adversarial examples.
method Inspired by fuzzy logic, new architectures combining alternative design elements.
result New models are more robust to adversarial examples and noise.
A RL-enhanced quantum-inspired algorithm solves combinatorial optimization problems.
problem Optimizing quantum-inspired algorithms for combinatorial problems.
method Reinforcement learning agent tunes hyperparameters of a quantum-inspired algorithm.
result The RL-enhanced algorithm samples high-quality solutions to the Ising problem.
A neuro-inspired architecture learns without supervision using clustering and predictive coding.
problem Achieving continual learning without supervision.
method Neuro-inspired architecture based on online clustering and hierarchical predictive coding.
result The architecture achieves continual learning without supervision.
Simplifies generating inspired images from deep models.
problem Lack of tools to quickly generate inspired images from deep models.
method Optimization method to find optimal latent parameters.
result Effective retrieval of inspired images in most cases.
Novel bio-inspired masking for robust speech emotion recognition.
problem Noise degradation in speech emotion recognition.
method Cochlear cepstrogram-based contrastive learning with temporal and frequency masking.
result Improved speech emotion recognition performance on K-EmoCon benchmark.
Paper classifies multiple video sources in encrypted tunnels using NLP-inspired features.
problem Traffic classification in encrypted video streams.
method Deep learning with a novel NLP-inspired feature for multi-label classification.
result The method achieves high performance on binary and multilabel classification tasks.
Neuro-inspired RL solves complex control problems with fewer controllers.
problem Solving nonlinear control problems with unknown dynamics efficiently.
method Hierarchical RL framework combining limb coordination and reinforcement learning.
result Local LQR controllers combined with a reinforcement learner solve global nonlinear problems.
MHVAE learns cross-modality inference inspired by human cognition.
problem Cross-modality inference in multimodal data.
method Hierarchical multimodal generative model with modality-specific and joint-modality distributions.
result MHVAE performs on par with state-of-the-art models on multimodal datasets.
New approach relaxes inductive biases of physics-inspired NNs for better performance.
problem Challenges in applying physics-inspired NNs to real-world systems.
method Examined and relaxed inductive biases of Hamiltonian NNs, improving performance on non-conservative systems.
result Improved performance on practical, non-conservative systems by relaxing inductive biases.
Quantum-inspired CCA improves correlation analysis for high-dimensional data.
problem High-dimensional data limits conventional CCA due to time complexity.
method Developed a quantum-inspired CCA (qiCCA) with logarithmic time complexity.
result qiCCA extracts more correlations than linear CCA and is comparable to deep and kernel CCA.
TMNs model brain memory systems for continual learning.
problem Catastrophic forgetting in neural networks.
method Triple Network architecture of GANs, incorporating brain-inspired algorithms.
result New state-of-the-art performance on class-incremental learning benchmarks.
Paper develops brain-inspired unsupervised learning for scalable object detection.
problem Machine vision systems struggle with object discovery and detection, especially under nonideal conditions.
method Leverages large-scale perceptual data to develop brain-inspired flexible, scale, and shift invariant object prototypes.
result Efficient unsupervised learning framework constructs accurate part-aware object models and robust detection algorithms.
Quantum-inspired model generates samples from data efficiently.
problem Unsupervised generative modeling from data.
method Matrix product states for efficient learning and direct sampling.
result Efficient direct sampling approach for generative tasks.
New neural network learns like humans without backpropagation.
problem Deep learning without backward error propagation.
method Biologically inspired feedforward supervisory signal.
result Effective learning from large amounts of feedforward information.
Paper generalizes path signature using fractional calculus for improved machine learning.
problem Improving path signature for machine learning applications.
method Introduces two new signatures inspired by fractional calculus and machine learning considerations.
result Significant accuracy improvements in handwritten digit recognition.
Smoothly prepares quantum states for robust machine learning.
problem Efficiently preparing quantum states for machine learning.
method Smoothed analysis to prove constant query state preparation.
result State preparation can be achieved with constant queries under realistic noise conditions.
New tensor network models learn continuous data effectively.
problem Tensor network models' limitations in handling continuous data.
method Developed a new family of tensor network generative models for continuous data.
result Models can approximate any reasonably smooth probability density function with arbitrary precision.
We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily a cumulative loss. This framework allows us to study a very general class of pro…
Spatially positioned neurons in neural networks mimic biological systems.
problem Creating neural networks that can perform multiple tasks efficiently.
method Added spatial positions and proximity penalties to artificial neurons.
result Neurons naturally cluster, each responsible for a specific task.
DCNs mimic neuronal networks for improved neural classification.
problem Lack of topological similarity between DNNs and biological neural networks.
method Developed DCNs with topologies inspired by real-world neuronal networks.
result High classification accuracy achieved by DCNs.
Deep-RLS uses deep learning to improve PCA for better source separation.
problem Improving PCA for better source separation in nonlinear systems.
method Inspired by RLS, Deep-RLS unfolds RLS iterations into a deep neural network.
result Deep-RLS significantly improves accuracy in recovering source signals.
A quantum-inspired classical algorithm speeds up LS-SVM classification.
problem Big data challenge in SVM classification.
method Improved indirect sampling technique for LS-SVM.
result Algorithm achieves logarithmic runtime for low rank data matrices.
Paper proposes a math-inspired L2O model for better generalization.
problem Overfitting and poor generalization of generic L2O models.
method Derived mathematical conditions for successful update rules and proposed a novel L2O model.
result Proposed model outperforms generic L2O models in out-of-distribution settings.
Proposes a new method for nonlinear models with robustness guarantees.
problem Distributional robustness in nonlinear models with causality.
method Representation learning and identifiable representation learning.
result First causality-inspired robustness method with finite-radius guarantees in nonlinear settings.
A new sampler and temperature estimation method enable efficient learning of Boltzmann Machines.
problem Efficient learning of Boltzmann Machines (BMs) is challenging due to high training costs and difficulty in parallelization.
method Proposed a new Boltzmann sampler (Langevin SB, LSB) and an efficient method (Conditional Expectation Matching, CEM) for estimating inverse temperature.
result Established an efficient learning framework (Sampler-Adaptive Learning, SAL) for BMs with greater expressive power than Restricted Boltzmann Machines (RBMs).
CoNBONet improves reliability analysis of complex systems with fast, energy-efficient predictions.
problem Time-dependent reliability analysis of nonlinear systems under stochastic excitations is computationally demanding.
method CoNBONet combines deep operator networks with neuroscience-inspired neuron models for fast, energy-efficient inference.
result CoNBONet provides reliable coverage of failure probabilities with theoretical guarantees.
BCIQT model improves ML prediction effectiveness using quantum theory.
problem Improving prediction effectiveness in machine learning models.
method Proposes Binary Classifier Inspired by Quantum Theory (BCIQT) model.
result BCIQT model outperforms state-of-the-art models in recall.
Develops a multi-class classifier using quantum detection theory.
problem Improving multi-class classification models in machine learning.
method Inspired by quantum detection theory, develops a multi-class classifier.
result Demonstrates improved effectiveness of multi-class classification models.
New algorithms improve MCMC efficiency for complex distributions.
problem High variance and low effective sample size in MCMC samplers.
method Antithetic Riemannian Manifold and Quantum-Inspired Hamiltonian Monte Carlo.
result Improved effective sample size and variance reduction.
In this paper we propose a multi-armed bandit inspired, pool based active learning algorithm for the problem of binary classification. By carefully constructing an analogy between active learning and multi-armed bandits, we utilize ideas such as lower confidence bounds, and self-concordant regularization from the multi…
Enhances ZSL models with biologically inspired feature enhancement.
problem Limited training data leads to poor feature extraction from pre-trained models.
method Dual-channel learning framework using auxiliary data sets.
result Improves ZSL model's generalization ability and achieves state-of-the-art results.
Novel chaotic neurons improve AI with minimal training data.
problem Limited training data for AI algorithms.
method Intrinsically chaotic neurons inspired by chaos theory.
result Classification accuracy up to 95.8% with just 2 training samples per class.
Paper proposes an iterative NAS technique inspired by Boolean function learning.
problem Challenges in Neural Architecture Search (NAS).
method Inspired by algorithms for learning low-degree sparse Boolean functions.
result Validated on DARTs and NAS-Bench-201, providing theoretical analysis.
BioHash improves similarity search performance using sparse high-dimensional hash codes.
problem Improving similarity search performance in high-dimensional data.
method BioHash produces sparse high-dimensional hash codes through a data-driven approach based on synaptic plasticity.
result BioHash outperforms previous hashing methods in various similarity search tasks.
A novel algorithm optimizes sparsity in reservoir computing inspired by insect brain.
problem Optimizing sparsity in reservoir computing networks.
method Inspired by insect brain, the algorithm optimizes sparsity levels by adjusting node firing thresholds.
result The algorithm outperforms standard gradient descent on tasks involving better classification, memorization, and convergence.
Quantum-inspired method optimizes portfolio selection.
problem Optimizing asset allocation in finance.
method Combining quantum-inspired and conventional optimization methods.
result Faster and more accurate portfolio optimization solutions.
Fibonacci Ensembles use Fibonacci weights to improve ensemble learning, inspired by natural growth patterns.
problem Improving ensemble learning methods to enhance model performance and interpretability.
method Introduces Fibonacci weights and a recursive ensemble dynamic to reduce variance and enrich representational depth.
result Fibonacci weighting can match or improve upon uniform averaging in ensemble learning experiments.
New neural network learns adaptive behaviors inspired by neuromodulation.
problem Current AI lacks the ability to adapt to changing environments.
method Inspired by cellular neuromodulation, a new deep neural network architecture is designed.
result Neuromodulation-based networks improve adaptation in meta-reinforcement learning tasks.
SiamJEPA uses Siamese student encoders to improve JEPA-based representation learning.
problem Improving self-supervised representation learning in JEPA models.
method Proposes SiamJEPA with masked Siamese student encoders and EMA teacher network.
result Siamese student encoders improve representation separability and learning speed.
Optimizes machine learning and system identification for real-world physical systems.
problem Estimating parameters in complex, real-world physical systems.
method Combines classical system identification and modern machine learning techniques using optimization-based approaches.
result Developed regularization strategies to incorporate prior knowledge into flexible models.
Neural SVEs model complex systems with memory, outperforming traditional methods.
problem Modeling systems with memory effects and irregular behavior.
method Introducing neural stochastic Volterra equations as a physics-inspired architecture.
result Neural SVEs outperform neural SDEs and DeepONets in various applications.
The paper proposes a bio-inspired framework for better compression and adversarial robustness in machine learning models.
problem Machine learning models are vulnerable to adversarial examples.
method The paper introduces a bio-inspired classification framework that conditions model inference on label hypothesis and uses an information bottleneck regularizer.
result The framework enables better compression and adversarial robustness without loss of natural accuracy.
CODA uses a new dropout technique inspired by constructivism learning to improve deep learning performance.
problem Existing dropout methods fail to differentiate among instances, leading to overfitting.
method CODA incorporates structural information and uses a Bayesian nonparametric method to create a better dropout technique.
result CODA outperformed other state-of-the-art dropout techniques on 5 real-world datasets.
This workshop explores the interface between cognitive neuroscience and recent advances in AI fields that aim to reproduce human performance such as natural language processing and computer vision, and specifically deep learning approaches to such problems. When studying the cognitive capabilities of the brain, scienti…
PerceptNet mimics human vision to estimate image quality.
problem Estimating perceptual distance between images and their perturbations.
method Inspired by human visual system, PerceptNet uses convolutional neural network architecture.
result PerceptNet outperforms traditional image quality metrics and deep learning methods.