The convenient access to copious multi-faceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-based learning, i.e., causal machine le...
详细信息
The convenient access to copious multi-faceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-based learning, i.e., causal machine learning (causal learning). Recent years have therefore witnessed great effort in developing causal learning algorithms aiming to help AI achieve human-level intelligence. Due to the lack-of ground-truth data, one of the biggest challenges in current causal learning research is algorithm evaluations. This largely impedes the cross-pollination of AI and causal inference, and hinders the two fields to benefit from the advances of the other. To bridge from conventional causal inference (i.e., based on statistical methods) to causal learning with big data (i.e., the intersection of causal inference and machine learning), in this survey, we review commonly-used datasets, evaluation methods, and measures for causal learning using an evaluation pipeline similar to conventional machine learning. We focus on the two fundamental causal-inference tasks and causality-aware machine learning tasks. Limitations of current evaluation procedures are also discussed. We then examine popular causal inference tools/packages and conclude with primary challenges and opportunities for benchmarking causal learning algorithms in the era of big data. The survey seeks to bring to the forefront the urgency of developing publicly available benchmarks and consensus-building standards for causal learning evaluation with observational data. In doing so, we hope to broaden the discussions and facilitate collaboration to advance the innovation and application of causal learning. Impact Statement—Causal learning goes beyond machine learning due to its power of uncovering data generating processes. Causality relates to crucial open problems in machine learning. On the opposite, machine learning contributes to addressing fundamental challenges in causal inference. One key challenge of causal
Artificial intelligence(AI)and robotics have gone through three generations of development,from Turing test,logic theory machine,to expert system and self-driving *** the third-generation today,AI and robotics have co...
详细信息
Artificial intelligence(AI)and robotics have gone through three generations of development,from Turing test,logic theory machine,to expert system and self-driving *** the third-generation today,AI and robotics have collaboratively been used in many areas in our society,including industry,business,manufacture,research,and *** are many challenging problems in developing AI and robotics *** launch this new Journal of Artificial Intelligence and Technology to facilitate the exchange of the latest research and practice in AI and *** this inaugural issue,we first introduce a few key technologies and platforms supporting the third-generation AI and robotics application development based on stacks of technologies and *** present examples of such development environments created by both industry and *** also selected eight papers in the related areas to celebrate the foundation of this journal.
Smart contract is a set of digital executable protocols intended to make contractual clauses partially or fully self-executing, self-enforcing, or both. As the second-generation blockchain technology, smart contracts ...
详细信息
The anatomical landmarking on statistical shape models is widely used in structural and morphometric analyses. The current study focuses on leveraging geometric features to realize an automatic and reliable landmarkin...
详细信息
This paper investigates the interaction of non-expert stakeholders with Artificial Intelligence (AI) in the energy urban domain, using the VIRTSI model and focusing on the capabilities of ChatGPT. VIRTSI (Variability ...
详细信息
ISBN:
(数字)9798350368833
ISBN:
(纸本)9798350368840
This paper investigates the interaction of non-expert stakeholders with Artificial Intelligence (AI) in the energy urban domain, using the VIRTSI model and focusing on the capabilities of ChatGPT. VIRTSI (Variability and Impact of Reciprocal Trust States towards Intelligent systems), is a rigorous computational model for human-AI Interaction that simulates human trust states, spanning from overtrust to distrust, through user modelling and quantifies the efficiency of the interaction in VIRTSI-adapted confusion matrices. The research employed an 16-question survey, evaluating the accuracy and usefulness of ChatGPT's responses regarding energy consumption, cost-effective solutions, and renewable energy production for residential buildings in Greece. Each answer was assessed by human stakeholders who were non-expert in the energy Urban Domain (e.g house owners, building managers, etc.), who either accepted or rejected the responses based on validation processes. The analysis highlighted key aspects such as repetition, specification, and objections in the interaction with ChatGPT, offering insights into the effectiveness of AI in supporting energy-related decisions. The findings reveal that while AI can provide valuable information, user validation and expert consultation are critical for practical implementation. This highlights both the potential and limitations of integrating AI tools like ChatGPT in enhancing non-expert stakeholder engagement and decision-making in urban energy management, emphasizing the ongoing need for human expert involvement.
Action languages are formal models of parts of natural language that are designed to describe effects of actions. Many of these languages can be viewed as high-level notations of answer set programs structured to repr...
详细信息
Prior work on generating explanations in a planning context has focused on providing the rationale behind an AI agent’s decision-making. While these methods offer the right explanations, they fail to heed the cogniti...
详细信息
Prior work on generating explanations in a planning context has focused on providing the rationale behind an AI agent’s decision-making. While these methods offer the right explanations, they fail to heed the cognitive requirement of understanding an explanation from the explainee or human’s perspective. In this work, we set out to address this issue by considering the order for communicating information in an explanation, or the progressiveness of making explanations. Progression is the notion of building complex concepts on simpler ones, which is known to benefit learning. In this work, we investigate a similar effect when an explanation is composed of multiple parts that are communicated sequentially. The challenge here lies in determining the order for receiving different parts of an explanation that would assist in understanding. Given the sequential nature, a formulation based on goal-based MDP is presented. The reward function of this MDP is learned via inverse reinforcement learning based on training data. We evaluated our approach in an escape-room domain to demonstrate its effectiveness. Upon analyzing the results, it revealed that the desired order arises strongly from both domain-dependent and independence features. This result confirmed our expectation that the process of understanding an explanation for planning tasks was progressive and context dependent. We also showed that the explanations generated using the learned rewards achieved better task performance and simultaneously reduced cognitive load. These results shed light on designing explainable robots across various domains.
We introduce a case study of a sustainability driven project involving a utility company based in Arizona. The company operates out of 22 facilities, which produce municipal solid waste hauled regularly by a waste hau...
详细信息
Smart home assistants are becoming a norm due to their ease-of-use. They employ spoken language as an interface, facilitating easy interaction with their users. Even with their obvious advantages, natural-language bas...
详细信息
ISBN:
(数字)9781728188997
ISBN:
(纸本)9781728189000
Smart home assistants are becoming a norm due to their ease-of-use. They employ spoken language as an interface, facilitating easy interaction with their users. Even with their obvious advantages, natural-language based interfaces are not prevalent outside the domain of home assistants. It is hard to adopt them for computer-controlled systems due to the numerous complexities involved with their implementation in varying fields. The main challenge is the grounding of natural language base terms into the underlying system's primitives. The existing systems that do use natural language interfaces are specific to one problem domain only. This paper presents a domain-agnostic framework that creates natural language interfaces for computer-controlled systems that have been developed by creating a customizable mapping between the language constructs and the system primitives. The framework employs ontologies built using OWL (Web Ontology Language) for knowledge representation and machine learning models for language processing tasks.
Batch Normalization (BN) is a well-known technique used in training deep neural networks. The main idea behind batch normalization is to normalize the features of the layers (i.e., transforming them to have a mean equ...
详细信息
Batch Normalization (BN) is a well-known technique used in training deep neural networks. The main idea behind batch normalization is to normalize the features of the layers (i.e., transforming them to have a mean equal to zero and a variance equal to one). Such a procedure encourages the optimization landscape of the loss function to be smoother, and improves the learning of the networks for both speed and performance. In this paper, we demonstrate that the performance of the network can be improved, if the distributions of the features of the output in the same layer are similar. As normalizing based on mean and variance does not necessarily make the features to have the same distribution, we propose a new normalization scheme: Batch Normalization with Skewness Reduction (BNSR). Comparing with other normalization approaches, BNSR transforms not just only the mean and variance, but also the skewness of the data. By tackling this property of a distribution, we are able to make the output distributions of the layers to be further similar. The nonlinearity of BNSR may further improve the expressiveness of the underlying network. Comparisons with other normalization schemes are tested on the CIFAR-100 and ImageNet datasets. Experimental results show that the proposed approach can outperform other state-of-the-arts that are not equipped with BNSR.
暂无评论