Spatiotemporal dynamics of odor representations in the human brain revealed by EEG decoding.

How the human brain translates olfactory inputs into diverse perceptions, from pleasurable floral smells to sickening smells of decay, is one of the fundamental questions in olfaction. To examine how different aspects of olfactory perception emerge in space and time in the human brain, we performed time-resolved multivariate pattern analysis of scalp-recorded electroencephalogram responses to 10 perceptually diverse odors and associated the resulting decoding accuracies with perception and source activities. Mean decoding accuracies of odors exceeded the chance level 100 ms after odor onset and reached maxima at 350 ms. The result suggests that the neural representations of individual odors were maximally separated at 350 ms. Perceptual representations emerged following the decoding peak: unipolar unpleasantness (neutral to unpleasant) from 300 ms, and pleasantness (neutral to pleasant) and perceptual quality (applicability to verbal descriptors such as "fruity" or "flowery") from 500 ms after odor onset, with all these perceptual representations reaching their maxima after 600 ms. A source estimation showed that the areas representing the odor information, estimated based on the decoding accuracies, were localized in and around the primary and secondary olfactory areas at 100 to 350 ms after odor onset. Odor representations then expanded into larger areas associated with emotional, semantic, and memory processing, with the activities of these later areas being significantly associated with perception. These results suggest that initial odor information coded in the olfactory areas (<350 ms) evolves into their perceptual realizations (300 to >600 ms) through computations in widely distributed cortical regions, with different perceptual aspects having different spatiotemporal dynamics.

Random forest machine-learning algorithm classifies white- and brown-rot fungi according to the number of the genes encoding Carbohydrate-Active enZyme families.

Wood-rotting fungi play an important role in the global carbon cycle because they are the only known organisms that digest wood, the largest carbon stock in nature. In the present study, we used linear discriminant analysis and random forest (RF) machine learning algorithms to predict white- or brown-rot decay modes from the numbers of genes encoding Carbohydrate-Active enZymes with over 98% accuracy. Unlike other algorithms, RF identified specific genes involved in cellulose and lignin degradation, including auxiliary activities (AAs) family 9 lytic polysaccharide monooxygenases, glycoside hydrolase family 7 cellobiohydrolases, and AA family 2 peroxidases, as critical factors. This study sheds light on the complex interplay between genetic information and decay modes and underscores the potential of RF for comparative genomics studies of wood-rotting fungi. IMPORTANCE: Wood-rotting fungi are categorized as either white- or brown-rot modes based on the coloration of decomposed wood. The process of classification can be influenced by human biases. The random forest machine learning algorithm effectively distinguishes between white- and brown-rot fungi based on the presence of Carbohydrate-Active enZyme genes. These findings not only aid in the classification of wood-rotting fungi but also facilitate the identification of the enzymes responsible for degrading woody biomass.

Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review.

In the rapidly evolving field of medical image analysis utilizing artificial intelligence (AI), the selection of appropriate computational models is critical for accurate diagnosis and patient care. This literature review provides a comprehensive comparison of vision transformers (ViTs) and convolutional neural networks (CNNs), the two leading techniques in the field of deep learning in medical imaging. We conducted a survey systematically. Particular attention was given to the robustness, computational efficiency, scalability, and accuracy of these models in handling complex medical datasets. The review incorporates findings from 36 studies and indicates a collective trend that transformer-based models, particularly ViTs, exhibit significant potential in diverse medical imaging tasks, showcasing superior performance when contrasted with conventional CNN models. Additionally, it is evident that pre-training is important for transformer applications. We expect this work to help researchers and practitioners select the most appropriate model for specific medical image analysis tasks, accounting for the current state of the art and future trends in the field.

Learning Intention-Aware Policies in Deep Reinforcement Learning.

Deep reinforcement learning (DRL) provides an agent with an optimal policy so as to maximize the cumulative rewards. The policy defined in DRL mainly depends on the state, historical memory, and policy model parameters. However, we humans usually take actions according to our own intentions, such as moving fast or slow, besides the elements included in the traditional policy models. In order to make the action-choosing mechanism more similar to humans and make the agent to select actions that incorporate intentions, we propose an intention-aware policy learning method in this letter To formalize this process, we first define an intention-aware policy by incorporating the intention information into the policy model, which is learned by maximizing the cumulative rewards with the mutual information (MI) between the intention and the action. Then we derive an approximation of the MI objective that can be optimized efficiently. Finally, we demonstrate the effectiveness of the intention-aware policy in the classical MuJoCo control task and the multigoal continuous chain walking task.

Learning With Proper Partial Labels.

Partial-label learning is a kind of weakly supervised learning with inexact labels, where for each training example, we are given a set of candidate labels instead of only one true label. Recently, various approaches on partial-label learning have been proposed under different generation models of candidate label sets. However, these methods require relatively strong distributional assumptions on the generation models. When the assumptions do not hold, the performance of the methods is not guaranteed theoretically. In this letter, we propose the notion of properness on partial labels. We show that this proper partial-label learning framework requires a weaker distributional assumption and includes many previous partial-label learning settings as special cases. We then derive a unified unbiased estimator of the classification risk. We prove that our estimator is risk consistent, and we also establish an estimation error bound. Finally, we validate the effectiveness of our algorithm through experiments.

Semisupervised Ordinal Regression Based on Empirical Risk Minimization.

Ordinal regression is aimed at predicting an ordinal class label. In this letter, we consider its semisupervised formulation, in which we have unlabeled data along with ordinal-labeled data to train an ordinal regressor. There are several metrics to evaluate the performance of ordinal regression, such as the mean absolute error, mean zero-one error, and mean squared error. However, the existing studies do not take the evaluation metric into account, restrict model choice, and have no theoretical guarantee. To overcome these problems, we propose a novel generic framework for semisupervised ordinal regression based on the empirical risk minimization principle that is applicable to optimizing all of the metrics mentioned above. In addition, our framework has flexible choices of models, surrogate losses, and optimization algorithms without the common geometric assumption on unlabeled data such as the cluster assumption or manifold assumption. We provide an estimation error bound to show that our risk estimator is consistent. Finally, we conduct experiments to show the usefulness of our framework.

Information-Theoretic Representation Learning for Positive-Unlabeled Classification.

Recent advances in weakly supervised classification allow us to train a classifier from only positive and unlabeled (PU) data. However, existing PU classification methods typically require an accurate estimate of the class-prior probability, a critical bottleneck particularly for high-dimensional data. This problem has been commonly addressed by applying principal component analysis in advance, but such unsupervised dimension reduction can collapse the underlying class structure. In this letter, we propose a novel representation learning method from PU data based on the information-maximization principle. Our method does not require class-prior estimation and thus can be used as a preprocessing method for PU classification. Through experiments, we demonstrate that our method, combined with deep neural networks, highly improves the accuracy of PU class-prior estimation, leading to state-of-the-art PU classification performance.

Classification From Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization.

Pairwise similarities and dissimilarities between data points are often obtained more easily than full labels of data in real-world classification problems. To make use of such pairwise information, an empirical risk minimization approach has been proposed, where an unbiased estimator of the classification risk is computed from only pairwise similarities and unlabeled data. However, this approach has not yet been able to handle pairwise dissimilarities. Semisupervised clustering methods can incorporate both similarities and dissimilarities into their framework; however, they typically require strong geometrical assumptions on the data distribution such as the manifold assumption, which may cause severe performance deterioration. In this letter, we derive an unbiased estimator of the classification risk based on all of similarities and dissimilarities and unlabeled data. We theoretically establish an estimation error bound and experimentally demonstrate the practical usefulness of our empirical risk minimization method.

Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs.

Summarizing large-scale directed graphs into small-scale representations is a useful but less-studied problem setting. Conventional clustering approaches, based on Min-Cut-style criteria, compress both the vertices and edges of the graph into the communities, which lead to a loss of directed edge information. On the other hand, compressing the vertices while preserving the directed-edge information provides a way to learn the small-scale representation of a directed graph. The reconstruction error, which measures the edge information preserved by the summarized graph, can be used to learn such representation. Compared to the original graphs, the summarized graphs are easier to analyze and are capable of extracting group-level features, useful for efficient interventions of population behavior. In this letter, we present a model, based on minimizing reconstruction error with nonnegative constraints, which relates to a Max-Cut criterion that simultaneously identifies the compressed nodes and the directed compressed relations between these nodes. A multiplicative update algorithm with column-wise normalization is proposed. We further provide theoretical results on the identifiability of the model and the convergence of the proposed algorithms. Experiments are conducted to demonstrate the accuracy and robustness of the proposed method.

Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting.

Deep learning is often criticized by two serious issues that rarely exist in natural nervous systems: overfitting and catastrophic forgetting. It can even memorize randomly labeled data, which has little knowledge behind the instance-label pairs. When a deep network continually learns over time by accommodating new tasks, it usually quickly overwrites the knowledge learned from previous tasks. Referred to as the neural variability, it is well known in neuroscience that human brain reactions exhibit substantial variability even in response to the same stimulus. This mechanism balances accuracy and plasticity/flexibility in the motor learning of natural nervous systems. Thus, it motivates us to design a similar mechanism, named artificial neural variability (ANV), that helps artificial neural networks learn some advantages from "natural" neural networks. We rigorously prove that ANV plays as an implicit regularizer of the mutual information between the training data and the learned model. This result theoretically guarantees ANV a strictly improved generalizability, robustness to label noise, and robustness to catastrophic forgetting. We then devise a neural variable risk minimization (NVRM) framework and neural variable optimizers to achieve ANV for conventional network architectures in practice. The empirical studies demonstrate that NVRM can effectively relieve overfitting, label noise memorization, and catastrophic forgetting at negligible costs.

Classification from Triplet Comparison Data.

Learning from triplet comparison data has been extensively studied in the context of metric learning, where we want to learn a distance metric between two instances, and ordinal embedding, where we want to learn an embedding in a Euclidean space of the given instances that preserve the comparison order as much as possible. Unlike fully labeled data, triplet comparison data can be collected in a more accurate and human-friendly way. Although learning from triplet comparison data has been considered in many applications, an important fundamental question of whether we can learn a classifier only from triplet comparison data without all the labels has remained unanswered. In this letter, we give a positive answer to this important question by proposing an unbiased estimator for the classification risk under the empirical risk minimization framework. Since the proposed method is based on the empirical risk minimization framework, it inherently has the advantage that any surrogate loss function and any model, including neural networks, can be easily applied. Furthermore, we theoretically establish an estimation error bound for the proposed empirical risk minimizer. Finally, we provide experimental results to show that our method empirically works well and outperforms various baseline methods.

Polynomial-Time Algorithms for Multiple-Arm Identification with Full-Bandit Feedback.

We study the problem of stochastic multiple-arm identification, where an agent sequentially explores a size-k subset of arms (also known as a super arm) from given n arms and tries to identify the best super arm. Most work so far has considered the semi-bandit setting, where the agent can observe the reward of each pulled arm or assumed each arm can be queried at each round. However, in real-world applications, it is costly or sometimes impossible to observe a reward of individual arms. In this study, we tackle the full-bandit setting, where only a noisy observation of the total sum of a super arm is given at each pull. Although our problem can be regarded as an instance of the best arm identification in linear bandits, a naive approach based on linear bandits is computationally infeasible since the number of super arms K is exponential. To cope with this problem, we first design a polynomial-time approximation algorithm for a 0-1 quadratic programming problem arising in confidence ellipsoid maximization. Based on our approximation algorithm, we propose a bandit algorithm whose computation time is O(log K), thereby achieving an exponential speedup over linear bandit algorithms. We provide a sample complexity upper bound that is still worst-case optimal. Finally, we conduct experiments on large-scale data sets with more than 1010 super arms, demonstrating the superiority of our algorithms in terms of both the computation time and the sample complexity.

Stochastic Multichannel Ranking with Brain Dynamics Preferences.

A driver's cognitive state of mental fatigue significantly affects his or her driving performance and more important, public safety. Previous studies have leveraged reaction time (RT) as the metric for mental fatigue and aim at estimating the exact value of RT using electroencephalogram (EEG) signals within a regression model. However, due to the easily corrupted and also nonsmooth properties of RTs during data collection, methods focusing on predicting the exact value of a noisy measurement, RT generally suffer from poor generalization performance. Considering that human RT is the reflection of brain dynamics preference (BDP) rather than a single regression output of EEG signals, we propose a novel channel-reliability-aware ranking (CArank) model for the multichannel ranking problem. CArank learns from BDPs using EEG data robustly and aims at preserving the ordering corresponding to RTs. In particular, we introduce a transition matrix to characterize the reliability of each channel used in the EEG data, which helps in learning with BDPs only from informative EEG channels. To handle large-scale EEG signals, we propose a stochastic-generalized expectation maximum (SGEM) algorithm to update CArank in an online fashion. Comprehensive empirical analysis on EEG signals from 40 participants shows that our CArank achieves substantial improvements in reliability while simultaneously detecting noisy or less informative EEG channels.

Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities.

Sufficient dimension reduction (SDR) is aimed at obtaining the low-rank projection matrix in the input space such that information about output data is maximally preserved. Among various approaches to SDR, a promising method is based on the eigendecomposition of the outer product of the gradient of the conditional density of output given input. In this letter, we propose a novel estimator of the gradient of the logarithmic conditional density that directly fits a linear-in-parameter model to the true gradient under the squared loss. Thanks to this simple least-squares formulation, its solution can be computed efficiently in a closed form. Then we develop a new SDR method based on the proposed gradient estimator. We theoretically prove that the proposed gradient estimator, as well as the SDR solution obtained from it, achieves the optimal parametric convergence rate. Finally, we experimentally demonstrate that our SDR method compares favorably with existing approaches in both accuracy and computational efficiency on a variety of artificial and benchmark data sets.

Bias Reduction and Metric Learning for Nearest-Neighbor Estimation of Kullback-Leibler Divergence.

Nearest-neighbor estimators for the Kullback-Leiber (KL) divergence that are asymptotically unbiased have recently been proposed and demonstrated in a number of applications. However, with a small number of samples, nonparametric methods typically suffer from large estimation bias due to the nonlocality of information derived from nearest-neighbor statistics. In this letter, we show that this estimation bias can be mitigated by modifying the metric function, and we propose a novel method for learning a locally optimal Mahalanobis distance function from parametric generative models of the underlying density distributions. Using both simulations and experiments on a variety of data sets, we demonstrate that this interplay between approximate generative models and nonparametric techniques can significantly improve the accuracy of nearest-neighbor-based estimation of the KL divergence.

Direct Estimation of the Derivative of Quadratic Mutual Information with Application in Supervised Dimension Reduction.

A typical goal of linear-supervised dimension reduction is to find a low-dimensional subspace of the input space such that the projected input variables preserve maximal information about the output variables. The dependence-maximization approach solves the supervised dimension-reduction problem through maximizing a statistical dependence between projected input variables and output variables. A well-known statistical dependence measure is mutual information (MI), which is based on the Kullback-Leibler (KL) divergence. However, it is known that the KL divergence is sensitive to outliers. Quadratic MI (QMI) is a variant of MI based on the [Formula: see text] distance, which is more robust against outliers than the KL divergence, and a computationally efficient method to estimate QMI from data, least squares QMI (LSQMI), has been proposed recently. For these reasons, developing a supervised dimension-reduction method based on LSQMI seems promising. However, not QMI itself but the derivative of QMI is needed for subspace search in linear-supervised dimension reduction, and the derivative of an accurate QMI estimator is not necessarily a good estimator of the derivative of QMI. In this letter, we propose to directly estimate the derivative of QMI without estimating QMI itself. We show that the direct estimation of the derivative of QMI is more accurate than the derivative of the estimated QMI. Finally, we develop a linear-supervised dimension-reduction algorithm that efficiently uses the proposed derivative estimator and demonstrate through experiments that the proposed method is more robust against outliers than existing methods.

Theoretical and Experimental Analyses of Tensor-Based Regression and Classification.

We theoretically and experimentally investigate tensor-based regression and classification. Our focus is regularization with various tensor norms, including the overlapped trace norm, the latent trace norm, and the scaled latent trace norm. We first give dual optimization methods using the alternating direction method of multipliers, which is computationally efficient when the number of training samples is moderate. We then theoretically derive an excess risk bound for each tensor norm and clarify their behavior. Finally, we perform extensive experiments using simulated and real data and demonstrate the superiority of tensor-based learning methods over vector- and matrix-based learning methods.

Regularized Multitask Learning for Multidimensional Log-Density Gradient Estimation.

Log-density gradient estimation is a fundamental statistical problem and possesses various practical applications such as clustering and measuring nongaussianity. A naive two-step approach of first estimating the density and then taking its log gradient is unreliable because an accurate density estimate does not necessarily lead to an accurate log-density gradient estimate. To cope with this problem, a method to directly estimate the log-density gradient without density estimation has been explored and demonstrated to work much better than the two-step method. The objective of this letter is to improve the performance of this direct method in multidimensional cases. Our idea is to regard the problem of log-density gradient estimation in each dimension as a task and apply regularized multitask learning to the direct log-density gradient estimator. We experimentally demonstrate the usefulness of the proposed multitask method in log-density gradient estimation and mode-seeking clustering.

An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions.

We consider the learning problem under an online Markov decision process (MDP) aimed at learning the time-dependent decision-making policy of an agent that minimizes the regret-the difference from the best fixed policy. The difficulty of online MDP learning is that the reward function changes over time. In this letter, we show that a simple online policy gradient algorithm achieves regret O(√T) for T steps under a certain concavity assumption and O(log T) under a strong concavity assumption. To the best of our knowledge, this is the first work to present an online MDP algorithm that can handle continuous state, action, and parameter spaces with guarantee. We also illustrate the behavior of the proposed online policy gradient method through experiments.

Direct Density Derivative Estimation.

Estimating the derivatives of probability density functions is an essential step in statistical data analysis. A naive approach to estimate the derivatives is to first perform density estimation and then compute its derivatives. However, this approach can be unreliable because a good density estimator does not necessarily mean a good density derivative estimator. To cope with this problem, in this letter, we propose a novel method that directly estimates density derivatives without going through density estimation. The proposed method provides computationally efficient estimation for the derivatives of any order on multidimensional data with a hyperparameter tuning method and achieves the optimal parametric convergence rate. We further discuss an extension of the proposed method by applying regularized multitask learning and a general framework for density derivative estimation based on Bregman divergences. Applications of the proposed method to nonparametric Kullback-Leibler divergence approximation and bandwidth matrix selection in kernel density estimation are also explored.