DeepProbCEP: A neuro-symbolic approach for complex event processing in adversarial settings

Vilamala, Marc Roig; Xing, Tianwei; Taylor, Harrison; García, Luis Antonio Ribot; Srivastava, Mani; Kaplan, Lance; Preece, Alun; Kimmig, Angelika; Cerutti, Federico

doi:10.1016/j.eswa.2022.119376

Cited by 10 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More in detail, Yang et al [21] present a novel learning approach for neuro-symbolic programs, showing its robustness against input perturbations in terms of provably safe portion of the learned model. In this context, NeSy robustness against adversarial attacks represents a popular area of research with several works aiming at proving either qualitatively [22] or quantitatively [23] the safety of NeSy approaches. Most of these works define robustness in terms of accuracy degradation over varying input perturbation intensity, independently of the input perturbation type and magnitude.…”

Section: B Robustnessmentioning

confidence: 99%

Measuring Trustworthiness in Neuro-Symbolic Integration

Agiollo,

Omicini

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Neuro-symbolic integration of symbolic and subsymbolic techniques represents a fast-growing AI trend aimed at mitigating the issues of neural networks in terms of decision processes, reasoning, and interpretability. Several state-of-theart neuro-symbolic approaches aim at improving performance, most of them focusing on proving their effectiveness in terms of raw predictive performance and/or reasoning capabilities. Meanwhile, few efforts have been devoted to increasing model trustworthiness, interpretability, and efficiency-mostly due to the complexity of measuring effectively improvements in terms of trustworthiness and interpretability. This is why here we analyse and discuss the need for ad-hoc trustworthiness metrics for neurosymbolic techniques. We focus on two popular paradigms mixing subsymbolic computation and symbolic knowledge, namely: (i) symbolic knowledge extraction (SKE), aimed at mapping subsymbolic models into human-interpretable knowledge bases; and (ii) symbolic knowledge injection (SKI), aimed at forcing subsymbolic models to adhere to a given symbolic knowledge. We first emphasise the need for assessing neuro-symbolic approaches from a trustworthiness perspective, highlighting the research challenges linked with this evaluation and the need for ad-hoc trust definitions. Then we summarise recent developments in SKE and SKI metrics focusing specifically on several trustworthiness pillars such as interpretability, efficiency, and robustness of neuro-symbolic methods. Finally, we highlight open research opportunities towards reliable and flexible trustworthiness metrics for neuro-symbolic integration.

show abstract

Section: B Robustnessmentioning

confidence: 99%

Measuring Trustworthiness in Neuro-Symbolic Integration

Agiollo,

Omicini

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…Furthermore, these approaches have been applied to solve complex tasks like semantic image interpretation [8] and event recognition from different data sources (e.g. video [1,2] and audio [22]). Inspired by [2], we encode the background knowledge about the behaviour of each appliance as a mixed integer linear programming problem (MILP), and use it to refine the prediction of the neural network.…”

Section: State Of the Artmentioning

confidence: 99%

A Neuro-Symbolic Approach for Non-Intrusive Load Monitoring

Apriceno,

Erculiani,

Passerini

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

A requirement of Smart Grids is the ability to predict the energy consumption patterns of their users. In the residential domain, this is usually not feasible due to the inability of the grid to dialog with (legacy) domestic appliances. To overcome this issue Non Intrusive Load Monitoring (NILM) was introduced, a task in which a predictor is used to disaggregate household power consumption. Many of the newer approaches make use of Neural Networks to accomplish this task, due to their superior ability to detect patterns in temporal (thus sequential) data. These models unfortunately require a huge amount of data to achieve good performance, and have the tendency to overfit the training data, making them difficult to predict future consumptions. For these reasons, adapting them to optimally predict a (future) house’s consumption requires expensive and often prohibitive data collection phases. We propose a solution in the form of a neuro-symbolic framework that refines neural network predictions via a constrained optimization problem modelling the characteristics of the appliances of a house. This combined approach achieves superior performance with respect to the neural network alone over two out of five appliances and comparable results for the remaining ones, without requiring further training data.

show abstract

"Challenges and future in deep learning for sentiment analysis: a comprehensive review and a proposed novel hybrid approach"

Islam,

Kabir,

Ghani

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Social media is used to categorise products or services, but analysing vast comments is time-consuming. Researchers use sentiment analysis via natural language processing, evaluating methods and results conventionally through literature reviews and assessments. However, our approach diverges by offering a thorough analytical perspective with critical analysis, research findings, identified gaps, limitations, challenges and future prospects specific to deep learning-based sentiment analysis in recent times. Furthermore, we provide in-depth investigation into sentiment analysis, categorizing prevalent data, pre-processing methods, text representations, learning models, and applications. We conduct a thorough evaluation of recent advances in deep learning architectures, assessing their pros and cons. Additionally, we offer a meticulous analysis of deep learning methodologies, integrating insights on applied tools, strengths, weaknesses, performance results, research gaps, and a detailed feature-based examination. Furthermore, we present in a thorough discussion of the challenges, drawbacks, and factors contributing to the successful enhancement of accuracy within the realm of sentiment analysis. A critical comparative analysis of our article clearly shows that capsule-based RNN approaches give the best results with an accuracy of 98.02% which is the CNN or RNN-based models. We implemented various advanced deep-learning models across four benchmarks to identify the top performers. Additionally, we introduced the innovative CRDC (Capsule with Deep CNN and Bi structured RNN) model, which demonstrated superior performance compared to other methods. Our proposed approach achieved remarkable accuracy across different databases: IMDB (88.15%), Toxic (98.28%), CrowdFlower (92.34%), and ER (95.48%). Hence, this method holds promise for automated sentiment analysis and potential deployment.

show abstract

DeepProbCEP: A neuro-symbolic approach for complex event processing in adversarial settings

Cited by 10 publications

References 16 publications

Measuring Trustworthiness in Neuro-Symbolic Integration

Measuring Trustworthiness in Neuro-Symbolic Integration

A Neuro-Symbolic Approach for Non-Intrusive Load Monitoring

"Challenges and future in deep learning for sentiment analysis: a comprehensive review and a proposed novel hybrid approach"

Contact Info

Product

Resources

About