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

Implementation flaws in cryptographic libraries, design flaws in underlying cryptographic primitives, and weaknesses in protocols using both, can all lead to exploitable vulnerabilities in software. Manually fixing such issues is…

This paper presents a new Python library called Automated Learning for Insightful Comparison and Evaluation (ALICE), which merges conventional feature selection and the concept of inter-rater agreeability in a simple, user-friendly manner…

In-context learning (ICL) has emerged as a powerful capability of transformer-based language models, enabling them to perform tasks by conditioning on a small number of examples presented at inference time, without any parameter updates.…

Nowadays, deep neural networks are being used in many domains because of their high accuracy results. However, they are considered as "black box", means that they are not explainable for humans. On the other hand, in some tasks such as…

Although graph-based learning has attracted a lot of attention, graph representation learning is still a challenging task whose resolution may impact key application fields such as chemistry or biology. To this end, we introduce GRALE, a…

Inner interpretability is a promising field aiming to uncover the internal mechanisms of AI systems through scalable, automated methods. While significant research has been conducted on large language models, limited attention has been paid…

Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structure or computation information of the neural architectures.…

This work proposes a novel Graph-based neural ArchiTecture Encoding Scheme, a.k.a. GATES, to improve the predictor-based neural architecture search. Specifically, different from existing graph-based schemes, GATES models the operations as…

This paper presents an overview of the verification framework ALICE in its current version 0.7. It is based on the generic theorem prover Isabelle [Pau03a]. Within ALICE a software or hardware component is specified as a state-full…

Interpreting a large number of neurons in deep learning is difficult. Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbitrary layer of neurons or subsets thereof. It uses a decoder…

Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning.…

In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator (ACE), our proposed method incorporates angular information that is inherently…

Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches to map nodes into a…

The remarkable performance of convolutional neural networks (CNNs) is entangled with their huge number of uninterpretable parameters, which has become the bottleneck limiting the exploitation of their full potential. Towards network…

Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, their black-box nature reduces interpretability, which limits…

Monumental advances in deep learning have led to unprecedented achievements across various domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial.…

Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical…

Neurons in auto-regressive language models like GPT-2 can be interpreted by analyzing their activation patterns. Recent studies have shown that techniques such as dictionary learning, a form of post-hoc sparse coding, enhance this…

Despite the success of Transformers on language understanding, code generation, and logical reasoning, they still fail to generalize over length on basic arithmetic tasks such as addition and multiplication. A major reason behind this…

Recent advancements in Intrusion Detection Systems (IDS), integrating Explainable AI (XAI) methodologies, have led to notable improvements in system performance via precise feature selection. However, a thorough understanding of…