Imbalanced learning(IL),i.e.,learning unbiased models from class-imbalanced data, is a challenging problem.

Neural backdoor attack is emerging as a severe security threat to deep learning, while the capability of existing defense methods is limited, especially for complex backdoor triggers. In the work, we explore the space formed by the pixel values of all possible backdoor triggers. An original trigger used by an attacker to build the backdoored model represents only a point in the space. It then will be generalized into a distribution of valid triggers, all of which can influence the backdoored model. Thus, previous methods that model only one point of the trigger distribution is not sufficient.

Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from unstable performance, poor applicability, and high computational cost in complex tasks where their assumptions do not hold. In this paper, we introduce a novel ensemble IL framework named MESA. It adaptively resamples the training set in iterations to get multiple classifiers and forms a cascade ensemble model. MESA directly learns the sampling strategy from data to optimize the final metric beyond following random heuristics.

For example, a backdoor attack uses one trigger to manipulate the model's outputs on all inputs,

It is a complex and time-consuming task, particularly when it involves large-scale landscapes, which are getting more common with the current boom in popularity of open world games. The current state-of-the-art (SOT A) in terrain modeling relies mainly on procedural and simulation methods [8], which rarely scale well beyond a certain point (compute expensive or lack of realism) and can easily fail to capture the variety of the landscape the world offers. The recent advances in generative machine learning and especially in the area of diffusion models have paved the way for models that can learn a representation of Earth's landscapes directly from real terrain data. By abstracting the complexity of the underlying physical processes, generative models can learn to reproduce patterns and mutual dependencies between visual features, which can lead to* First author high levels of perceptual realism. This work explores the potential of following a similar data-centric methodology for a joint domain of terrain surface model and optical reflectance.

Advanced slot and winding designs are imperative to create future high performance electrical machines (EM). As a result, the development of methods to design and improve slot filling factor (SFF) has attracted considerable research. Recent developments in manufacturing processes, such as additive manufacturing and alternative materials, has also highlighted a need for novel high-fidelity design techniques to develop high performance complex geometries and topologies. This study therefore introduces a novel physics-informed machine learning (PIML) design optimization process for improving SFF in traction electrical machines used in electric vehicles. A maximum entropy sampling algorithm (MESA) is used to seed a physics-informed Bayesian optimization (PIBO) algorithm, where the target function and its approximations are produced by Gaussian processes (GP)s. The proposed PIBO-MESA is coupled with a 2D finite element model (FEM) to perform a GP-based surrogate and provide the first demonstration of the optimal combination of complex design variables for an electrical machine. Significant computational gains were achieved using the new PIBO-MESA approach, which is 45% faster than existing stochastic methods, such as the non-dominated sorting genetic algorithm II (NSGA-II). The FEM results confirm that the new design optimization process and keystone shaped wires lead to a higher SFF (i.e. by 20%) and electromagnetic improvements (e.g. maximum torque by 12%) with similar resistivity. The newly developed PIBO-MESA design optimization process therefore presents significant benefits in the design of high-performance electric machines, with reduced development time and costs.

The authors propose to address this issue by using a meta/ensemble-learning framework. In this framework, the meta-algorithm deduces an appropriate data sampling strategy that generates a data set for a new base learner to train. The meta-learner is trained using reinforcement learning. The meta-state is composed of two histograms that are respectively the empirical distributions of the training and validation error. The meta-sampler uses this state to sample a coefficient.