Paper shows using unlabeled mismatched images can improve KD for image classification.
problem Improving Knowledge Distillation for image classification with limited labeled data.
method Used unlabeled mismatched images as stimulus for KD, focusing on stimulus complexity.
result Stimulus complexity is crucial for KD's effectiveness, as demonstrated on MNIST and CIFAR datasets.
Model explains optical illusions using geometric sub-Riemannian geodesics.
problem Understanding and explaining geometrical optical illusions.
method Neuro-mathematical model based on sub-Riemannian geodesics in the Roto-Translation Group.
result Illusory contours are described as geodesics in a new metric.
Neural network memorizes external stimuli through synaptic strength changes.
problem Memory and classification in neural networks.
method One-to-one mapping between stimulus and synaptic strength under synaptic plasticity constraints.
result Neural network can memorize external stimuli through synaptic changes.
Neurons in cortical circuits exhibit coordinated spiking activity, and can produce correlated synchronous spikes during behavior and cognition. We recently developed a method for estimating the dynamics of correlated ensemble activity by combining a model of simultaneous neuronal interactions (e.g., a spin-glass model)…
New method decomposes sensory information from neurons into specific stimuli and features.
problem Understanding how much and what specific information neurons encode.
method Introduced axioms for meaningful stimulus-wise decomposition and derived a tractable solution using diffusion models.
result Can efficiently estimate contributions of specific stimuli and features to encoded information.
The article explores how organisms and machines learn and recognize the world using Bayesian inference and thermodynamics.
problem Understanding how organisms and machines learn and recognize the world.
method Introducing a thermodynamic view of the Bayesian brain hypothesis, using a simple generative model of spiking neural populations.
result The process of Bayesian inference can be quantified using entropy, revealing the perceptual capacity of neural activity.
The study analyzes neural interactions using an Ising model to reveal contributions of pairwise interactions to sparseness and fluctuation.
problem Understanding the contributions of pairwise interactions to sparseness and fluctuation in neural activity.
method Inference methods for a time-dependent Ising model to analyze neural interactions and estimate time-dependent neural interactions with credible intervals.
result Pairwise interactions contribute to increasing sparseness and fluctuation in neural activity.
Study reveals resilience of Chinese guarantee network during financial crisis and stimulus.
problem Limited knowledge about guarantee network dynamics during financial downturn.
method Analyzed comprehensive bank loan dataset covering 80% of total loans in China.
result Guarantee network became smaller, less connected, and more stable during financial crisis.
Study shows stock price interactions increase during crises due to external stimulus.
problem Understanding stock price interactions during economic crises.
method Granger Causality and recurrence analysis on stock price series.
result External stimulus drives stock price interactions during crises.
Bayesian correlated component analysis identifies brain process similarities across multiple stimulus views.
problem Investigating brain process similarity in responses to multiple views of a stimulus.
method Hierarchical probabilistic model that evaluates universality of spatial networks across multi-view data.
result Bayesian correlated component analysis evaluates favorably against other algorithms and identifies variability in spatial representations.
VR game data for P300 BCI with raccoon vs demon stimuli.
problem Developing confidence metrics for P300 BCI.
method Multiclass labeled P300 dataset in VR game context.
result Estimation of model's confidence in stimulus predictions.
During the Great Recession, Democrats in the United States argued that government spending could be utilized to "grease the wheels" of the economy in order to create wealth and to increase employment; Republicans, on the other hand, contended that government spending is wasteful and discouraged investment, thereby incr…
Estimates brain connectivity networks from natural stimuli, controlling type I error.
problem Estimating brain connectivity networks from natural stimuli with nuisance signals.
method Estimating stimulus-locked brain network by treating non-stimulus-induced signals as nuisance parameters. Testing maximum degree of network using inferential method.
result Proves type I error can be controlled and power increases asymptotically.
Study uses simulation-based inference to decode brain activity from synthetic stimuli.
problem Reversing the process of brain activity emulation to recover stimuli or their properties.
method Pairing brain emulator with LLMs to learn a probabilistic mapping from brain maps to stimulus parameters.
result LLMs can serve as controllable stimulus generators and parameters can be recovered from brain maps.
Ordinal embedding methods estimate perceptual scales from relative judgments.
problem Measuring subjective sensation using relative judgments.
method Ordinal embedding from machine learning applied to method of triads.
result Ordinal embedding allows estimating perceptual scales from few judgments, non-monotonous functions, and multi-dimensional scales.
Experiments that study neural encoding of stimuli at the level of individual neurons typically choose a small set of features present in the world --- contrast and luminance for vision, pitch and intensity for sound --- and assemble a stimulus set that systematically varies along these dimensions. Subsequent analysis o…
New algorithm reduces performance loss in IRL with mismatched transition dynamics.
problem Performance degradation in inverse reinforcement learning due to mismatched transition dynamics.
method Proposed a robust Maximum Causal Entropy (MCE) IRL algorithm leveraging robust reinforcement learning insights.
result Empirically demonstrated stable performance improvement under transition dynamics mismatches.
Venice used 'helicopter money' to subsidize during famine and plague, but it caused instability.
problem Subsidizing inhabitants during containment policies while preventing long-term debt increase.
method Net-worth helicopter money strategy, equivalent to monetary expansion generating losses to the issuer.
result The strategy caused much monetary instability and had to be quickly reversed.
Causal terminology is often introduced in the interpretation of encoding and decoding models trained on neuroimaging data. In this article, we investigate which causal statements are warranted and which ones are not supported by empirical evidence. We argue that the distinction between encoding and decoding models is n…
New method allows sheets to morph into multiple shapes via spatially varying stimuli.
problem Limitation of current shape-programmed sheets to achieve only one target geometry.
method Patterning the stimulus itself for spatiotemporal control over local deformation magnitudes.
result A single physical sample can be induced to traverse a continuous family of target geometries.
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.
problem Theoretical guarantees for score-mismatched diffusion models in zero-shot conditional sampling.
method Theoretical analysis of score-mismatched diffusion models and zero-shot conditional samplers.
result Theoretical performance guarantees with explicit dimensional dependencies for score-mismatched diffusion samplers.
Paper identifies objective mismatch in MBRL, affecting control task performance.
problem Objective mismatch in MBRL framework affects control task performance.
method Proposes re-weighting dynamics model training to mitigate mismatch.
result Likelihood of one-step ahead predictions is not always correlated with control performance.
Brain decoding involves the determination of a subject's cognitive state or an associated stimulus from functional neuroimaging data measuring brain activity. In this setting the cognitive state is typically characterized by an element of a finite set, and the neuroimaging data comprise voluminous amounts of spatiotemp…
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.
Functional neuroimaging can measure the brain?s response to an external stimulus. It is used to perform brain mapping: identifying from these observations the brain regions involved. This problem can be cast into a linear supervised learning task where the neuroimaging data are used as predictors for the stimulus. Brai…
New framework assesses neural sensitivity to small perturbations.
problem Comparing neural representations' sensitivity to small changes.
method Local decodable information, Fisher information, and projected pullback/Fisher metric.
result Reveals differences in neural sensitivity not captured by activation alignment.
Paper classifies plant electrical signals to identify external stimuli.
problem Classifying external stimuli using plant electrical response.
method Computed 11 statistical features from plant electrical signals and used discriminant analysis.
result Raw electrical signals contain enough information for stimulus classification.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
In order to interact intelligently with objects in the world, animals must first transform neural population responses into estimates of the dynamic, unknown stimuli which caused them. The Bayesian solution to this problem is known as a Bayes filter, which applies Bayes' rule to combine population responses with the pr…
New method addresses error bounds for PnP-ULA under mismatched models.
problem Error bounds for PnP-ULA under mismatched measurement and prior models.
method Posterior-L2 pseudometric to quantify error bounds.
result Explicit error bound for PnP-ULA under mismatched posterior distribution.
The workshop explores AI and neuroscience, focusing on complex stimuli and neural network models.
problem Understanding and modeling brain function using AI and machine learning.
method Combining cognitive neuroscience with AI techniques like deep learning and attention mechanisms.
result The need for rich vector representations of stimuli for effective machine learning.
Paper addresses linear regression with partially mismatched data using local search with theoretical guarantees.
problem Linear regression with partially mismatched data.
method Optimization formulation and greedy local search algorithm with theoretical guarantees.
result Local search algorithm converges to nearly-optimal solution at a linear rate under certain conditions.
The Mismatch Principle improves Lasso robustness to model uncertainties.
problem Estimation robustness under model misspecifications.
method Generalized Lasso with the Mismatch Principle.
result The Mismatch Principle provides robust error bounds for Lasso.
Machine learning improves design verification, achieving better coverage than random methods.
problem Limited coverage of complex designs using random or constrained-random stimulus.
method Supervised and reinforcement learning applied to constrained-random DV tools.
result Machine learning enhances DV to achieve better coverage and faster timescales.
PACMAN provides bounds for classification tasks considering accuracy vs. negative log-loss mismatch.
problem Mismatch between accuracy and negative log-loss in classification tasks.
method Point-wise PAC approach over generalization gap, using likelihood ratio and concentration inequalities.
result PACMAN provides point-wise PAC bounds for the generalization problem.
End-to-end denoising framework improves SDR and PESQ metrics.
problem Spectrum and metric mismatches in speech enhancement networks.
method Optimizes network on time-domain signals after ISTFT and uses improved loss functions.
result Significantly improved SDR and PESQ performance.
Deep learning predicts mismatched ratings in Amazon reviews.
problem Identifying reviews with mismatched ratings on Amazon.
method Converted reviews to vectors using paragraph vector, trained a recurrent neural network with gated recurrent unit, incorporated semantic relationships.
result Model accurately predicts rating mismatches and provides feedback.
Study on LMMSE estimation with model mismatch, quantifying MSE trade-offs.
problem Model mismatch in LMMSE estimation with undermodeling.
method Analyzing the average MSE of LMMSE estimation with random regressors.
result Performance improvement depends on sufficient samples and model complexity.
Paper proposes a method to handle linear regression with partially shuffled data.
problem Linear regression with mismatched predictors and responses.
method Pseudo-likelihood approach based on two-component mixture densities with EM optimization.
result The method can tolerate larger fractions of mismatches and estimate noise level.
Deep neural networks decode natural visual scenes from neural spikes.
problem Decoding visual scenes from neural spikes for brain-machine interfaces.
method Developed a novel spike-image decoder (SID) using deep neural networks.
result SID reconstructs natural visual scenes from neural spikes with high accuracy.
Unified understanding of neural representation similarity measures.
problem Fragmented research landscape of neural network similarity measures.
method Observation and exploration of connections between shape distances and normalized Bures similarity.
result Cosine of the Riemannian shape distance equals normalized Bures similarity.
Voice conversion methods degrade in noisy conditions, with BLFWAS outperforming others.
problem Robustness of voice conversion techniques under mismatched conditions.
method Comparative analysis of five VC techniques on CMU ARCTIC corpus, exploring speech enhancement techniques.
result Bilinear frequency warping with amplitude scaling (BLFWAS) outperforms other methods in noisy conditions.
A new method handles mismatched data in multivariate regression.
problem Handling mismatched data in multivariate linear regression.
method Two-stage approach: first stage estimates parameters, second stage estimates permutation.
result Permutation recovery conditions become less stringent with increasing number of responses.
Unified framework for imitating tasks across domains with discrepancies.
problem Learning tasks across domains with embodiment, viewpoint, and dynamics mismatches.
method Two-step approach: alignment followed by adaptation. Alignment uses Generative Adversarial MDP Alignment (GAMA) for state and action correspondences from unpaired, unaligned demonstrations. Adaptation leverages these correspondences for zero-shot imitation.
result Effectiveness of the proposed approach in embodiment, viewpoint, and dynamics mismatch scenarios.
Deep transfer learning improves sleep staging with small datasets.
problem Insufficient data for deep neural networks due to channel mismatch.
method Transfer learning from large to small datasets, finetuning the pretrained network.
result Significant performance improvement in sleep staging.
Ensemble models improve prediction calibration for mismatched distributions.
problem Calibration issues in deep neural networks with mismatched train and test distributions.
method Simple data augmentation and mixing techniques for ensemble models.
result Improves calibration and accuracy on CIFAR10 and CIFAR100 benchmarks.
New method corrects state distribution mismatch for off-policy policy optimization.
problem Mismatch between behavior and evaluation policy state distributions.
method Off-policy policy gradient with state distribution correction.
result Significantly improved policy quality in simulations.