Related papers: Dynamic Automated Deduction by Contradiction Separ…
The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is often possible to approximate the input-output relations…
Answer set programs used in real-world applications often require that the program is usable with different input data. This, however, can often lead to contradictory statements and consequently to an inconsistent program. Causes for…
How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To…
Counterfactual explanations (CEs) enhance the interpretability of machine learning models by describing what changes to an input are necessary to change its prediction to a desired class. These explanations are commonly used to guide users'…
Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence. However, symbolic reasoning is still a great challenge for deep learning models, which often…
Edge detection (ED) is a fundamental perceptual process in computer vision, forming the structural basis for high-level reasoning tasks such as segmentation, recognition, and scene understanding. Despite substantial progress achieved by…
Target speech extraction (TSE) focuses on extracting the speech of a specific target speaker from a mixture of signals. Existing TSE models typically utilize static embeddings as conditions for extracting the target speaker's voice.…
In this paper, we present a novel method for dynamically expanding Convolutional Neural Networks (CNNs) during training, aimed at meeting the increasing demand for efficient and sustainable deep learning models. Our approach, drawing from…
Data augmentation techniques have been proven useful in many applications in NLP fields. Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our work, we present AugCSE, a unified framework to utilize…
This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units. We view the subword segmentation of output sentences as a latent variable that should be marginalized out…
We mechanize, in the proof assistant Isabelle, a proof of the axiom-scheme of Separation in generic extensions of models of set theory by using the fundamental theorems of forcing. We also formalize the satisfaction of the axioms of…
Predictive process analytics often apply machine learning to predict the future states of a running business~process. However, the internal mechanisms of many existing predictive algorithms are opaque and a human decision-maker is unable to…
Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars. One of the principal benefits of…
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…
We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov…
In sequential recommendation systems, data augmentation and contrastive learning techniques have recently been introduced using diffusion models to achieve robust representation learning. However, most of the existing approaches use random…
Counterfactual explanations (CFEs) are a popular approach for interpreting machine learning predictions by identifying minimal feature changes that alter model outputs. However, in real-world settings, users often refine feasibility…
Although deep neural networks have made remarkable achievements in the field of automatic modulation recognition (AMR), these models often require a large amount of labeled data for training. However, in many practical scenarios, the…
In computer science, divide and conquer (D&C) is an algorithm design paradigm based on multi-branched recursion. A D&C algorithm works by recursively and monotonically breaking down a problem into sub problems of the same (or a related)…
The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…