C-Net: A Method for Generating Non-deterministic and Dynamic Multivariate Decision Trees

Abbass, Hussein A.; Towsey, Michael; Finn, G. D.

doi:10.1007/pl00011665

Cited by 16 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques derive from the area of neural networks [1,3,19,29,32,38] support vector machines and decision trees [2,4], fuzzy logic-based approaches [10,15] and Ant Colony Optimization (ACO) algorithms [23]. Among them, DiagNN presented the third better accuracy (97.9%) over the WDBC dataset, while a hybrid approach of a neural network with fuzzy logicbased rules called Feature Space Mapping [3] and a neural network architecture based on evolutionary programming called MPANN [1], presented slightly better accuracy (98.3 and 98.1%, respectively).…”

Section: Comparison With Other Techniquesmentioning

confidence: 99%

Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances

Anagnostopoulos

2006

Med Bio Eng Comput

View full text Add to dashboard Cite

This paper deals with breast cancer diagnostic and prognostic estimations employing neural networks over the Wisconsin Breast Cancer datasets, which consist of measurements taken from breast cancer microscopic instances. A probabilistic approach is dedicated to solve the diagnosis problem, detecting malignancy among instances derived from the Fine Needle Aspirate test, while regression algorithms estimate the time interval that possibly correspond to the right end-point of the patients' disease-free survival time or the time where the tumour recurs (time-to-recur). For the diagnosis problem, the accuracy of the neural network in terms of sensitivity and specificity was measured at 98.6 and 97.5% respectively, using the leave-one-out test method. As far as the prognosis problem is concerned, the accuracy of the neural network was measured through a stratified tenfold cross-validation approach. Sensitivity ranged between 80.5 and 91.8%, while specificity ranged between 91.9 and 97.9%, depending on the tested fold and the partition of the predicted period. The prognostic recurrence predictions were then further evaluated using survival analysis and compared with other techniques found in literature.

show abstract

Section: Comparison With Other Techniquesmentioning

confidence: 99%

Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances

Anagnostopoulos

2006

Med Bio Eng Comput

View full text Add to dashboard Cite

show abstract

“…Decision trees have been used with neural networks to build an interpretable model that explains the decision-making process of neural-networks. The C-Net algorithm, proposed by Abbass et al (2001), is one of those early algorithms which uses a univariate decision tree (UDT) to generate a multivariate decision tree (MDT) from neural networks. In this paper, we propose a modification of the algorithm into a deep version of C-Net to extract the rules from DNNs.…”

Section: C-net: An Approach To Learn Multivariate Decision Trees From...mentioning

confidence: 99%

Towards Interpretable ANNs: An Exact Transformation to Multi-Class Multivariate Decision Trees

Nguyen¹,

Kasmarik²,

Abbass³

2020

Preprint

View full text Add to dashboard Cite

Deep neural networks (DNNs) are commonly labelled as black-boxes lacking interpretability; thus, hindering human's understanding of DNNs' behaviors. A need exists to generate a meaningful sequential logic for the production of a specific output. Decision trees exhibit better interpretability and expressive power due to their representation language and the existence of efficient algorithms to generate rules. Growing a decision tree based on the available data could produce larger than necessary trees or trees that do not generalise well. In this paper, we introduce two novel multivariate decision tree (MDT) algorithms for rule extraction from a DNN: an Exact-Convertible Decision Tree (EC-DT) and a Deep C-Net algorithm to transform a neural network with Rectified Linear Unit activation functions into a representative tree which can be used to extract multivariate rules for reasoning. While the EC-DT translates the DNN in a layer-wise manner to represent exactly the decision boundaries implicitly learned by the hidden layers of the network, the Deep C-Net inherits the decompositional approach from EC-DT and combines with a C5 tree learning algorithm to construct the decision rules. The results suggest that while EC-DT is superior in preserving the structure and the accuracy of DNN, C-Net generates the most compact and highly effective trees from DNN. Both proposed MDT algorithms generate rules including combinations of multiple attributes for precise interpretation of decision-making processes.

show abstract

“…However, it is not possible to use a classic neural network to justify an action, as the agent must be able to re-encode the learnt artificial neural network into another representation (e.g. a decision tree or propositional logic) that will enable the agent to reason in relation to its actions [ 72 ]. Different situations will necessitate different representations and models.…”

Section: Open Challenges For Ta and Cocysmentioning

confidence: 99%

“…An action can be generated using an artificial neural network, and when questioned about the action, classic reasoning can be used based on a symbolic knowledge base. To ensure that the two models are consistent in their behaviours, it is important that forms of rule extraction from the neural network are used to construct a knowledge base [ 72 ] and maximise consistency and compatibility. Uncertainty Management Uncertainty is a major concern in the design of a Cookie and may occur for a variety of reasons, including due to a Cookie’s limited knowledge of another Cookie or an environment, the levels of abstraction and fidelity a Cookie employs in one or more internal models, the deliberate deceptive actions from other Cookies or the nature of the context within which it is embedded.…”

Section: Open Challenges For Ta and Cocysmentioning

confidence: 99%

Section: Open Challenges For Ta and Cocysmentioning

confidence: 99%

See 1 more Smart Citation

Trusted Autonomy and Cognitive Cyber Symbiosis: Open Challenges

et al. 2015

View full text Add to dashboard Cite

This paper considers two emerging interdisciplinary, but related topics that are likely to create tipping points in advancing the engineering and science areas. Trusted Autonomy (TA) is a field of research that focuses on understanding and designing the interaction space between two entities each of which exhibits a level of autonomy. These entities can be humans, machines, or a mix of the two. Cognitive Cyber Symbiosis (CoCyS) is a cloud that uses humans and machines for decision-making. In CoCyS, human-machine teams are viewed as a network with each node comprising humans (as computational machines) or computers. CoCyS focuses on the architecture and interface of a Trusted Autonomous System. This paper examines these two concepts and seeks to remove ambiguity by introducing formal definitions for these concepts. It then discusses open challenges for TA and CoCyS, that is, whether a team made of humans and machines can work in fluid, seamless harmony.

show abstract

C-Net: A Method for Generating Non-deterministic and Dynamic Multivariate Decision Trees

Cited by 16 publications

References 19 publications

Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances

Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances

Towards Interpretable ANNs: An Exact Transformation to Multi-Class Multivariate Decision Trees

Trusted Autonomy and Cognitive Cyber Symbiosis: Open Challenges

Contact Info

Product

Resources

About