A Memory Model for Concept Hierarchy Representation and Commonsense Reasoning

Most associative memory models perform one level mapping between predefined sets of input and output patterns1 and are unable to represent hierarchical knowledge. Complex AI systems allow hierarchical representation of concepts, but generally do not have learning capabilities. In this paper, a memory model is proposed which forms concept hierarchy by learning sample relations between concepts. All concepts are represented in a concept layer. Relations between a concept and its defining lower level concepts, are chunked as cognitive codes represented in a coding layer. By updating memory contents in the concept layer through code firing in the coding layer, the system is able to perform an important class of commonsense reasoning, namely recognition and inheritance.

Incremental learning from stream data

Recent years have witnessed an incredibly increasing interest in the topic of incremental learning. Unlike conventional machine learning situations, data flow targeted by incremental learning becomes available continuously over time. Accordingly, it is desirable to be able to abandon the traditional assumption of the availability of representative training data during the training period to develop decision boundaries. Under scenarios of continuous data flow, the challenge is how to transform the vast amount of stream raw data into information and knowledge representation, and accumulate experience over time to support future decision-making process. In this paper, we propose a general adaptive incremental learning framework named ADAIN that is capable of learning from continuous raw data, accumulating experience over time, and using such knowledge to improve future learning and prediction performance. Detailed system level architecture and design strategies are presented in this paper. Simulation results over several real-world data sets are used to validate the effectiveness of this method.

Combining diverse knowledge: The role of specialist and generalist learning

Purpose
– The aim of this paper is to contribute to understanding the nature of specialist and generalist human capital by exploring the ways in which knowledge workers view their experience of working in specialist and generalist roles in pharmaceutical firms in Ireland and the UK.

Design/methodology/approach
– The findings are based on interviews with 55 knowledge workers employed in a range of scientific, technical and managerial positions in four Irish and two UK firms located in the pharmaceutical sector. Interviews were also conducted with nine human resource/training and development managers within these six firms.

Findings
– The findings suggest that the categorisation of human capital as either specialist or generalist is too rigid and does not take account of the fact that individuals may themselves choose to shape their careers by investing in a range of education, training and development opportunities that will enable them to move between specialist and generalist roles.

Originality/value
– The paper unpacks the concepts of specialist and generalist human capital from an employee perspective and challenges the sharp distinction that is made between specialist and generalist human capital.

COD and NH4-N Estimation in the Inflow of Wastewater Treatment Plants using Machine Learning Techniques

The in-line measurement of COD and NH4-N in the WWTP inflow is crucial for the timely monitoring of biological wastewater treatment processes and for the development of advanced control strategies for optimized WWTP operation. As a direct measurement of COD and NH4-N requires expensive and high maintenance in-line probes or analyzers, an approach estimating COD and NH4-N based on standard and spectroscopic in-line inflow measurement systems using Machine Learning Techniques is presented in this paper. The results show that COD estimation using Radom Forest Regression with a normalized MSE of 0.3, which is sufficiently accurate for practical applications, can be achieved using only standard in-line measurements. In the case of NH4-N, a good estimation using Partial Least Squares Regression with a normalized MSE of 0.16 is only possible based on a combination of standard and spectroscopic in-line measurements. Furthermore, the comparison of regression and classification methods shows that both methods perform equally well in most cases.

Knowledge representation for data integration and exploration in translational medicine

Tese de doutoramento, Informática (Bioinformática), Universidade de Lisboa, Faculdade de Ciências, 2014