The blood-brain barrier (BBB) serves as a protective barrier that separates the brain from the circulatory system, regulating the passage of substances into the central nervous system. Assessing the BBB permeability of potential drugs is crucial for effective drug targeting. However, traditional experimental methods for measuring BBB permeability are challenging and impractical for large-scale screening. Consequently, there is a need to develop computational approaches to predict BBB permeability. This paper proposes a GPS Transformer architecture augmented with Self Attention, designed to perform well in the low-data regime. The proposed approach achieved a state-of-the-art performance on the BBB permeability prediction task using the BBBP dataset, surpassing existing models. With a ROC-AUC of 78.8%, the approach sets a state-of-the-art by 5.5%. We demonstrate that standard Self Attention coupled with GPS transformer performs better than other variants of attention coupled with GPS Transformer.

Clinically deployed deep learning-based segmentation models are known to fail on data outside of their training distributions. While clinicians review the segmentations, these models tend to perform well in most instances, which could exacerbate automation bias. Therefore, detecting out-of-distribution images at inference is critical to warn the clinicians that the model likely failed. This work applied the Mahalanobis distance (MD) post hoc to the bottleneck features of four Swin UNETR and nnU-net models that segmented the liver on T1-weighted magnetic resonance imaging and computed tomography. By reducing the dimensions of the bottleneck features with either principal component analysis or uniform manifold approximation and projection, images the models failed on were detected with high performance and minimal computational load. In addition, this work explored a non-parametric alternative to the MD, a k-th nearest neighbors distance (KNN). KNN drastically improved scalability and performance over MD when both were applied to raw and average-pooled bottleneck features.

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite their different natures, these strategies often lead to comparable performance gains. However, little is known about whether they induce similar representations inside LLMs. We approach this problem by analyzing the probability landscape of their hidden representations in the two cases. More specifically, we compare how LLMs solve the same question-answering task, finding that ICL and SFT create very different internal structures, in both cases undergoing a sharp transition in the middle of the network. In the first half of the network, ICL shapes interpretable representations hierarchically organized according to their semantic content. In contrast, the probability landscape obtained with SFT is fuzzier and semantically mixed. In the second half of the model, the fine-tuned representations develop probability modes that better encode the identity of answers, while the landscape of ICL representations is characterized by less defined peaks. Our approach reveals the diverse computational strategies developed inside LLMs to solve the same task across different conditions, allowing us to make a step towards designing optimal methods to extract information from language models.

The majority of automated machine learning (AutoML) solutions are developed in Python, however a large percentage of data scientists are associated with the R language. Unfortunately, there are limited R solutions available. Moreover high entry level means they are not accessible to everyone, due to required knowledge about machine learning (ML). To fill this gap, we present the forester package, which offers ease of use regardless of the user's proficiency in the area of machine learning. The forester is an open-source AutoML package implemented in R designed for training high-quality tree-based models on tabular data. It fully supports binary and multiclass classification, regression, and partially survival analysis tasks. With just a few functions, the user is capable of detecting issues regarding the data quality, preparing the preprocessing pipeline, training and tuning tree-based models, evaluating the results, and creating the report for further analysis.

Molecular sequence analysis is crucial for comprehending several biological processes, including protein-protein interactions, functional annotation, and disease classification. The large number of sequences and the inherently complicated nature of protein structures make it challenging to analyze such data. Finding patterns and enhancing subsequent research requires the use of dimensionality reduction and feature selection approaches. Recently, a method called Correlated Clustering and Projection (CCP) has been proposed as an effective method for biological sequencing data. The CCP technique is still costly to compute even though it is effective for sequence visualization. Furthermore, its utility for classifying molecular sequences is still uncertain. To solve these two problems, we present a Nearest Neighbor Correlated Clustering and Projection (CCP-NN)-based technique for efficiently preprocessing molecular sequence data. To group related molecular sequences and produce representative supersequences, CCP makes use of sequence-to-sequence correlations. As opposed to conventional methods, CCP doesn't rely on matrix diagonalization, therefore it can be applied to a range of machine-learning problems. We estimate the density map and compute the correlation using a nearest-neighbor search technique. We performed molecular sequence classification using CCP and CCP-NN representations to assess the efficacy of our proposed approach. Our findings show that CCP-NN considerably improves classification task accuracy as well as significantly outperforms CCP in terms of computational runtime.

Cyber-physical control systems are critical infrastructures designed around highly responsive feedback loops that are measured and manipulated by hundreds of sensors and controllers. Anomalous data, such as from cyber-attacks, greatly risk the safety of the infrastructure and human operators. With recent advances in the quantum computing paradigm, the application of quantum in anomaly detection can greatly improve identification of cyber-attacks in physical sensor data. In this paper, we explore the use of strong pre-processing methods and a quantum-hybrid Support Vector Machine (SVM) that takes advantage of fidelity in parameterized quantum circuits to efficiently and effectively flatten extremely high dimensional data. Our results show an F-1 Score of 0.86 and accuracy of 87% on the HAI CPS dataset using an 8-qubit, 16-feature quantum kernel, performing equally to existing work and 14% better than its classical counterpart.

Retrieval-augmented generation (RAG) has achieved significant success in information retrieval to assist large language models LLMs because it builds an external knowledge database. However, it also has many problems, it consumes a lot of memory because of the enormous database, and it cannot update the established index database in time when confronted with massive streaming data. To reduce the memory required for building the database and maintain accuracy simultaneously, we proposed a new approach integrating a streaming algorithm with k-means clustering into RAG. Our approach applied a streaming algorithm to update the index dynamically and reduce memory consumption. Additionally, the k-means algorithm clusters highly similar documents, and the query time would be shortened. We conducted comparative experiments on four methods, and the results indicated that RAG with streaming algorithm and k-means clusters outperforms traditional RAG in accuracy and memory, particularly when dealing with large-scale streaming data.

Machine learning techniques are widely used for estimating causal effects. Double/debiased machine learning (DML) (Chernozhukov et al., 2018) uses a double-robust score function that relies on the prediction of nuisance functions, such as the propensity score, which is the probability of treatment assignment conditional on covariates. Estimators relying on double-robust score functions are highly sensitive to errors in propensity score predictions. Machine learners increase the severity of this problem as they tend to over- or underestimate these probabilities. Several calibration approaches have been proposed to improve probabilistic forecasts of machine learners. This paper investigates the use of probability calibration approaches within the DML framework. Simulation results demonstrate that calibrating propensity scores may significantly reduces the root mean squared error of DML estimates of the average treatment effect in finite samples. We showcase it in an empirical example and provide conditions under which calibration does not alter the asymptotic properties of the DML estimator.

Early prediction of seizures and timely interventions are vital for improving patients' quality of life. While seizure prediction has been shown in software-based implementations, to enable timely warnings of upcoming seizures, prediction must be done on an edge device to reduce latency. Ideally, such devices must also be low-power and track long-term drifts to minimize maintenance from the user. This work presents SPIRIT: Stochastic-gradient-descent-based Predictor with Integrated Retraining and In situ accuracy Tuning. SPIRIT is a complete system-on-a-chip (SoC) integrating an unsupervised online-learning seizure prediction classifier with eight 14.4 uW, 0.057 mm2, 90.5 dB dynamic range, Zoom Analog Frontends. SPIRIT achieves, on average, 97.5%/96.2% sensitivity/specificity respectively, predicting seizures an average of 8.4 minutes before they occur. Through its online learning algorithm, prediction accuracy improves by up to 15%, and prediction times extend by up to 7x, without any external intervention. Its classifier consumes 17.2 uW and occupies 0.14 mm2, the lowest reported for a prediction classifier by >134x in power and >5x in area. SPIRIT is also at least 5.6x more energy efficient than the state-of-the-art.

The classification performance of the random vector functional link (RVFL), a randomized neural network, has been widely acknowledged. However, due to its shallow learning nature, RVFL often fails to consider all the relevant information available in a dataset. Additionally, it overlooks the geometrical properties of the dataset. To address these limitations, a novel graph random vector functional link based on two-view learning (GRVFL-2V) model is proposed. The proposed model is trained on multiple views, incorporating the concept of multiview learning (MVL), and it also incorporates the geometrical properties of all the views using the graph embedding (GE) framework. The fusion of RVFL networks, MVL, and GE framework enables our proposed model to achieve the following: i) \textit{efficient learning}: by leveraging the topology of RVFL, our proposed model can efficiently capture nonlinear relationships within the multi-view data, facilitating efficient and accurate predictions; ii) \textit{comprehensive representation}: fusing information from diverse perspectives enhance the proposed model's ability to capture complex patterns and relationships within the data, thereby improving the model's overall generalization performance; and iii) \textit{structural awareness}: by employing the GE framework, our proposed model leverages the original data distribution of the dataset by naturally exploiting both intrinsic and penalty subspace learning criteria. The evaluation of the proposed GRVFL-2V model on various datasets, including 27 UCI and KEEL datasets, 50 datasets from Corel5k, and 45 datasets from AwA, demonstrates its superior performance compared to baseline models. These results highlight the enhanced generalization capabilities of the proposed GRVFL-2V model across a diverse range of datasets.