相关论文: ALICE: An Interpretable Neural Architecture for Ge…

A new image encryption scheme using the advanced encryption standard (AES), a chaotic map, a genetic operator, and a fuzzy inference system is proposed in this paper. In this work, plain images were used as input, and the required security…

Due to the widespread use of complex machine learning models in real-world applications, it is becoming critical to explain model predictions. However, these models are typically black-box deep neural networks, explained post-hoc via…

Metaphor requires a language model to resolve a token whose contextual meaning diverges from its basic literal sense. Understanding how transformer models organize this reinterpretation across depth remains an open problem in mechanistic…

Text normalization is a ubiquitous process that appears as the first step of many Natural Language Processing problems. However, previous Deep Learning approaches have suffered from so-called silly errors, which are undetectable on…

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…

One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level…

Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks…

In cloud security, traditional searchable encryption (SE) requires high computation and communication overhead for dynamic search and update. The clever combination of machine learning (ML) and SE may be a new way to solve this problem.…

We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Unlike existing multi-task learning methodologies, the graph structure is not assumed…

Over-parameterized neural language models (LMs) can memorize and recite long sequences of training data. While such memorization is normally associated with undesired properties such as overfitting and information leaking, our work casts…

Tokenization is the first - and often underappreciated - layer of computation in language models. While Chain-of-Thought (CoT) prompting enables transformer models to approximate recurrent computation by externalizing intermediate steps, we…

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

Graph embedding provides an efficient solution for graph analysis by converting the graph into a low-dimensional space which preserves the structure information. In contrast to the graph structure data, the i.i.d. node embedding can be…

The renaissance of neural architecture search (NAS) has seen classical methods such as genetic algorithms (GA) and genetic programming (GP) being exploited for convolutional neural network (CNN) architectures. While recent work have…

When predictive models are used to support complex and important decisions, the ability to explain a model's reasoning can increase trust, expose hidden biases, and reduce vulnerability to adversarial attacks. However, attempts at…

Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing…

Tokenisation is the first step in almost all NLP tasks, and state-of-the-art transformer-based language models all use subword tokenisation algorithms to process input text. Existing algorithms have problems, often producing tokenisations…

We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once).…

Neural representations have emerged as a new paradigm for applications in rendering, imaging, geometric modeling, and simulation. Compared to traditional representations such as meshes, point clouds, or volumes they can be flexibly…

Grids allow users flexible on-demand usage of computing resources through remote communication networks. A remarkable example of a Grid in High Energy Physics (HEP) research is used in the ALICE experiment at European Organization for…