Next, we are going to cover several stages in one step, all are related to each other and it will make more sense. Previously we have seen the methods for signaling the beginning of a run and of an epoch. In every epoch, we have to iterate over the entire dataset, for various reasons related to both computational and convergence optimizations we do so in batches (mini-batch stochastic gradient descent). As such we have to log some information related to this step to our RunManager, which will help us to compute the overall loss and the accuracy for the entire epoch. Once the epoch finishes we have to compute the aforementioned metrics, save them to the local collection and log them to Tensorboard.

Reservoir computing is a machine learning paradigm that transforms the transient dynamics of high-dimensional nonlinear systems for processing time-series data. Although reservoir computing was initially proposed to model information processing in the mammalian cortex, it remains unclear how the non-random network architecture, such as the modular architecture, in the cortex integrates with the biophysics of living neurons to characterize the function of biological neuronal networks (BNNs). Here, we used optogenetics and fluorescent calcium imaging to record the multicellular responses of cultured BNNs and employed the reservoir computing framework to decode their computational capabilities. Micropatterned substrates were used to embed the modular architecture in the BNNs. We first show that modular BNNs can be used to classify static input patterns with a linear decoder and that the modularity of the BNNs positively correlates with the classification accuracy. We then used a timer task to verify that BNNs possess a short-term memory of ~1 s and finally show that this property can be exploited for spoken digit classification. Interestingly, BNN-based reservoirs allow transfer learning, wherein a network trained on one dataset can be used to classify separate datasets of the same category. Such classification was not possible when the input patterns were directly decoded by a linear decoder, suggesting that BNNs act as a generalization filter to improve reservoir computing performance. Our findings pave the way toward a mechanistic understanding of information processing within BNNs and, simultaneously, build future expectations toward the realization of physical reservoir computing systems based on BNNs.

The success of neural networks over the past decade has established them as effective models for many relevant data generating processes. Statistical theory on neural networks indicates graceful scaling of sample complexity. For example, Joen & Van Roy (arXiv:2203.00246) demonstrate that, when data is generated by a ReLU teacher network with $W$ parameters, an optimal learner needs only $\tilde{O}(W/\epsilon)$ samples to attain expected error $\epsilon$. However, existing computational theory suggests that, even for single-hidden-layer teacher networks, to attain small error for all such teacher networks, the computation required to achieve this sample complexity is intractable. In this work, we fit single-hidden-layer neural networks to data generated by single-hidden-layer ReLU teacher networks with parameters drawn from a natural distribution. We demonstrate that stochastic gradient descent (SGD) with automated width selection attains small expected error with a number of samples and total number of queries both nearly linear in the input dimension and width. This suggests that SGD nearly achieves the information-theoretic sample complexity bounds of Joen & Van Roy (arXiv:2203.00246) in a computationally efficient manner. An important difference between our positive empirical results and the negative theoretical results is that the latter address worst-case error of deterministic algorithms, while our analysis centers on expected error of a stochastic algorithm.

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.

Recently, many applications have been devoted to understanding and revealing causal rather than associative relations among variables. One approach in the context of time series is that of synthetic controls (Abadie and Gardeazabal, 2003) and various extensions. This is based on the idea of recovering the counterfactual outcome that would have been observed had an intervention not taken place. This article contributes to expanding and generalizing this class of models, allowing for non-linearity in a nonparametric manner through Gaussian Processes. These models have high degree of flexibility in building the counterfactual outcome, using all types of information and without any limitations on the functional form. They also make it possible to assess the robustness of the synthetic controls, as we can use the posterior distributions of the Gaussian Processes to quantify uncertainty stemming from the functional form estimation. Lastly, as the models learn the relationships which prevail amongst all associated variables, there is no need to match the time series on a calendar basis, making the most of the available data.

The estimation of heterogeneous treatment effects (HTEs) has attracted considerable interest in many disciplines, most prominently in medicine and economics. Contemporary research has so far primarily focused on continuous and binary responses where HTEs are traditionally estimated by a linear model, which allows the estimation of constant or heterogeneous effects even under certain model misspecifications. More complex models for survival, count, or ordinal outcomes require stricter assumptions to reliably estimate the treatment effect. Most importantly, the noncollapsibility issue necessitates the joint estimation of treatment and prognostic effects. Model-based forests allow simultaneous estimation of covariate-dependent treatment and prognostic effects, but only for randomized trials. In this paper, we propose modifications to model-based forests to address the confounding issue in observational data. In particular, we evaluate an orthogonalization strategy originally proposed by Robinson (1988, Econometrica) in the context of model-based forests targeting HTE estimation in generalized linear models and transformation models. We found that this strategy reduces confounding effects in a simulated study with various outcome distributions. We demonstrate the practical aspects of HTE estimation for survival and ordinal outcomes by an assessment of the potentially heterogeneous effect of Riluzole on the progress of Amyotrophic Lateral Sclerosis.

GBSVM (Granular-ball Support Vector Machine) is an important attempt to use the coarse granularity of a granular-ball as the input to construct a classifier instead of a data point. It is the first classifier whose input contains no points, i.e., $x_i$, in the history of machine learning. However, on the one hand, its dual model is not derived, and the algorithm has not been implemented and can not be applied. On the other hand, there are some errors in its existing model. To address these problems, this paper has fixed the errors of the original model of GBSVM, and derived its dual model. Furthermore, an algorithm is designed using particle swarm optimization algorithm to solve the dual model. The experimental results on the UCI benchmark datasets demonstrate that GBSVM has good robustness and efficiency.

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

One of the means to perform navigation is using a dead reckoning (DR) approach. In DR, given initial conditions, velocity or acceleration measurements are integrated to obtain the position. An inertial navigation system (INS) is the most popular tool working with DR principles. Its popularity stems from these facts: it provides a full navigation solution (position, velocity, and orientation), it is a standalone system capable of working in any environment (land, air, underground, underwater, indoors), and it is available in many different grades (ranging from low-cost low-performance to high-cost high-performance systems) [1-3].

Early identification of emergent topics is of eminent importance due to their potential impacts on society. There are many methods for detecting emerging terms and topics, all with advantages and drawbacks. However, there is no consensus about the attributes and indicators of emergence. In this study, we evaluate emerging topic detection in the field of artificial intelligence using a new method to evaluate emergence. We also introduce two new attributes of collaboration and technological impact which can help us use both paper and patent information simultaneously. Our results confirm that the proposed new method can successfully identify the emerging topics in the period of the study. Moreover, this new method can provide us with the score of each attribute and a final emergence score, which enable us to rank the emerging topics with their emergence scores and each attribute score.