Biomedical image segmentation is critical for precise structure delineation and downstream analysis. Traditional methods often struggle with noisy data, while deep learning models such as U-Net have set new benchmarks in segmentation performance. nnU-Net further automates model configuration, making it adaptable across datasets without extensive tuning. However, it requires a substantial amount of annotated data for cross-validation, posing a challenge when only raw images but no labels are available. Large foundation models offer zero-shot generalizability, but may underperform on specific datasets with unique characteristics, limiting their direct use for analysis. This work addresses these bottlenecks by proposing a data-centric AI workflow that leverages active learning and pseudo-labeling to combine the strengths of traditional neural networks and large foundation models while minimizing human intervention. The pipeline starts by generating pseudo-labels from a foundation model, which are then used for nnU-Net's self-configuration. Subsequently, a representative core-set is selected for minimal manual annotation, enabling effective fine-tuning of the nnU-Net model. This approach significantly reduces the need for manual annotations while maintaining competitive performance, providing an accessible solution for biomedical researchers to apply state-of-the-art AI techniques in their segmentation tasks. The code is available at https://github.com/MMV-Lab/AL_BioMed_img_seg.

Fault detection in electric motors is a critical challenge in various industries, where failures can result in significant operational disruptions. This study investigates the use of Recurrent Neural Networks (RNNs) and Bayesian Neural Networks (BNNs) for diagnosing motor damage using acoustic signal analysis. A novel approach is proposed, leveraging frequency domain representation of sound signals for enhanced diagnostic accuracy. The architectures of both RNNs and BNNs are designed and evaluated on real-world acoustic data collected from household appliances using smartphones. Experimental results demonstrate that BNNs provide superior fault detection performance, particularly for imbalanced datasets, offering more robust and interpretable predictions compared to traditional methods. The findings suggest that BNNs, with their ability to incorporate uncertainty, are well-suited for industrial diagnostic applications. Further analysis and benchmarks are suggested to explore resource efficiency and classification capabilities of these architectures.

Traditional neural networks (multi-layer perceptrons) have become an important tool in data science due to their success across a wide range of tasks. However, their performance is sometimes unsatisfactory, and they often require a large number of parameters, primarily due to their reliance on the linear combination structure. Meanwhile, additive regression has been a popular alternative to linear regression in statistics. In this work, we introduce novel deep neural networks that incorporate the idea of additive regression. Our neural networks share architectural similarities with Kolmogorov-Arnold networks but are based on simpler yet flexible activation and basis functions. Additionally, we introduce several hybrid neural networks that combine this architecture with that of traditional neural networks. We derive their universal approximation properties and demonstrate their effectiveness through simulation studies and a real-data application. The numerical results indicate that our neural networks generally achieve better performance than traditional neural networks while using fewer parameters.

This preliminary white paper proposes a novel 8-bit floating-point data format HiFloat8 (abbreviated as HiF8) for deep learning. HiF8 features tapered precision. For normal value encoding, it provides 7 exponent values with 3-bit mantissa, 8 exponent values with 2-bit mantissa, and 16 exponent values with 1-bit mantissa. For denormal value encoding, it extends the dynamic range by 7 extra powers of 2, from 31 to 38 binades (notice that FP16 covers 40 binades). Meanwhile, HiF8 encodes all the special values except that positive zero and negative zero are represented by only one bit-pattern. Thanks to the better balance between precision and dynamic range, HiF8 can be simultaneously used in both forward and backward passes of AI training. In this paper, we will describe the definition and rounding methods of HiF8, as well as the tentative training and inference solutions. To demonstrate the efficacy of HiF8, massive simulation results on various neural networks, including traditional neural networks and large language models (LLMs), will also be presented.

Fault monitoring and diagnostics are important to ensure reliability of electric motors. Efficient algorithms for fault detection improve reliability, yet development of cost-effective and reliable classifiers for diagnostics of equipment is challenging, in particular due to unavailability of well-balanced datasets, with signals from properly functioning equipment and those from faulty equipment. Thus, we propose to use a Bayesian neural network to detect and classify faults in electric motors, given its efficacy with imbalanced training data. The performance of the proposed network is demonstrated on real life signals, and a robustness analysis of the proposed solution is provided.

Through this comprehensive survey of Kolmogorov-Arnold Networks(KAN), we have gained a thorough understanding of its theoretical foundation, architectural design, application scenarios, and current research progress. KAN, with its unique architecture and flexible activation functions, excels in handling complex data patterns and nonlinear relationships, demonstrating wide-ranging application potential. While challenges remain, KAN is poised to pave the way for innovative solutions in various fields, potentially revolutionizing how we approach complex computational problems.

Despite the many successful applications of deep learning models for multidimensional signal and image processing, most traditional neural networks process data represented by (multidimensional) arrays of real numbers. The intercorrelation between feature channels is usually expected to be learned from the training data, requiring numerous parameters and careful training. In contrast, vector-valued neural networks are conceived to process arrays of vectors and naturally consider the intercorrelation between feature channels. Consequently, they usually have fewer parameters and often undergo more robust training than traditional neural networks. This paper aims to present a broad framework for vector-valued neural networks, referred to as V-nets. In this context, hypercomplex-valued neural networks are regarded as vector-valued models with additional algebraic properties. Furthermore, this paper explains the relationship between vector-valued and traditional neural networks. Precisely, a vector-valued neural network can be obtained by placing restrictions on a real-valued model to consider the intercorrelation between feature channels. Finally, we show how V-nets, including hypercomplex-valued neural networks, can be implemented in current deep-learning libraries as real-valued networks.

Deep Learning (DL) models have become popular for solving complex problems, but they have limitations such as the need for high-quality training data, lack of transparency, and robustness issues. Neuro-Symbolic AI has emerged as a promising approach combining the strengths of neural networks and symbolic reasoning. Symbolic knowledge injection (SKI) techniques are a popular method to incorporate symbolic knowledge into sub-symbolic systems. This work proposes solutions to improve the knowledge injection process and integrate elements of ML and logic into multi-agent systems (MAS).

Neural networks have revolutionized the field of artificial intelligence and machine learning. The emergence of transformers has further strengthened the capabilities of neural networks in natural language processing (NLP) and computer vision. The transformer architecture was introduced in 2017 by researchers at Google. It has since then been widely adopted in the development of various AI models, including those by OpenAI and DeepMind. In this article, we will explore how transformers work, their applications, and their impact on the future of AI.

When you start learning about AI in general, there's a probable knowledge roadmap you'll go through. Starting with statistics, some programming, diving into Machine Learning, and knowing about different models for different solutions, you finally reach Deep Learning, and this is where things change a bit. Yes, Deep Learning is also based on statistics and algorithms, and yes, you have to code things for them to work, but there are also different models that behave better on particular problems. Here come the well-known improvements from the traditional Neural Networks, which perform much better for certain types of data, and excel in certain tasks: Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). But, what is the main difference between these models?