Explainable AI (XAI) methods generally fall into two categories. Post-hoc approaches generate explanations for pre-trained models and are compatible with various neural network architectures. These methods often use feature importance visualizations, such as saliency maps, to indicate which input regions influenced the model’s prediction. Unfortunately, they typically offer a coarse understanding of the model’s decision-making process. In contrast, ante-hoc (inherently explainable) methods rely on specially designed model architectures trained from scratch. A notable subclass of these methods provides explanations through prototypes, representative patches extracted from the training data. However, prototype-based approaches require dedicated architectures, involve specialized training procedures, and perform well only on specific datasets. In this work, we propose EPIC (Explanation of Pretrained Image Classification), a novel approach that bridges the gap between these two paradigms. Like post-hoc methods, EPIC operates on pre-trained models without architectural modifications. Simultaneously, it delivers intuitive, prototype-based explanations inspired by ante-hoc techniques. To the best of our knowledge, EPIC is the first post-hoc method capable of fully replicating the core explanatory power of inherently interpretable models. We evaluate EPIC on benchmark datasets commonly used in prototype-based explanations, such as CUB-200-2011 and Stanford Cars, alongside large-scale datasets like ImageNet, typically employed by post-hoc methods. EPIC uses prototypes to explain model decisions, providing a flexible and easy-to-understand tool for creating clear, high-quality explanations.

Video processing is generally divided into two main categories: processing of the entire video, which typically yields optimal classification outcomes, and real-time processing, where the objective is to make a decision as promptly as possible. Although the models dedicated to the processing of entire videos are typically well-defined and clearly presented in the literature, this is not the case for online processing, where a plethora of hand-devised methods exist. To address this issue, we present PrAViC, a novel, unified, and theoretically-based adaptation framework for tackling the online classification problem in video data. The initial phase of our study is to establish a mathematical background for the classification of sequential data, with the potential to make a decision at an early stage. This allows us to construct a natural function that encourages the model to return a result much faster. The subsequent phase is to present a straightforward and readily implementable method for adapting offline models to the online setting using recurrent operations. Finally, PrAViC is evaluated by comparing it with existing state-of-the-art offline and online models and datasets. This enables the network to significantly reduce the time required to reach classification decisions while maintaining, or even enhancing, accuracy.

This study proposes a novel single-phase switched capacitor multilevel inverter structure for symmetrical and asymmetrical operation. The proposed configuration requires two DC sources, twelve switches, two flying capacitors, and a single diode to generate 9-level and 21-level output voltage. The proposed configuration features inherent self-voltage balancing without sensors, ensuring stable operation under varying conditions. The switched-capacitors enhance voltage gain (Vo=10Vdc) while reducing component count and switch stress. A single-carrier pulse width modulation (SC-PWM) method is utilized to minimize computation time and produce gating signals. The proposed topology is designed and simulated in PLECS software, incorporating thermal modeling to assess its efficiency and overall performance. The experimental setup was prepared, and a thorough comparative evaluation was carried out using dual-source-based topologies. The proposed topology demonstrates superior performance and enhanced design characteristics.

Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available.

This article presents an analysis of the two speed observer structures which are based on the backstepping and sliding super twisting approach. The observer stabilizing functions result from the Lyapunov theorem. To obtain the observer tuning gains the observer structure is linearized near the equilibrium point. The rotor angular speed is obtained from nonadaptive dependence. In the sensorless control system structure the classical PI controllers and transformation to the multiscalar variables are applied. The theoretical derivations are verified in experimental waveforms. Comparison of both speed observer structures is presented for nominal speed, load torque injections while regenerating mode, very low speed range and the uncertainties of nominal parameters of induction machine.

In the paper, we focus on ant-based clustering time series data represented by means of the so-called delta episode information systems. A clustering process is made on the basis of delta representation of time series, i.e., we are interested in char