Reference no: EM132837923
CIS006-2 Concepts and Technologies of Artificial Intelligence - University of Bedfordshire
Assignment: Random Search Optimisation and Meta Learning
Learning outcome 1: Identify and analyse efficient ways of solving a problem that requires to explore a large number of routes to find the best solution for a minimal number of steps
Learning outcome 2: Justify results of using at least two AI techniques capable of finding an acceptable solution to the given problem
Learning outcome 3: Evaluate and compare the performances of the techniques in terms of the number of steps required for finding a solution to the problem
Task
Students will use one or more strategies such as: (1) R andom Search, (2) Meta Learning, (3) Adaptive Boosting, or (4) Cascade Correlation to optimise the structure and parameters of Artificial Neural Networks (ANNs) on a given benchmark problem. Such optimisation is required to maximise the recognition accuracy of ANNs designed for solving biometric tasks. In practice the optimal structure and parameters of ANNs are difficult to find because of the needs of multiple experiments with the different numbers of principal components, hidden neurons, learning rate, and types of gradient algorithms.
COVID related alternatives
There are alternatives which students can find interesting within the unit scope.
Method and Technology
Students will attempt to optimise ANNs which were manually designed in Assignment 1. To achieve the goal, students will apply one or more optimisation strategies with different parameters. The examples of the Random Search, Meta Learning, Adaptive Boosting as well as MATLAB search strategies are provided in the unit tutorials. Advanced students can use Python, MATLAB, or R to optimise Deep Learning, Convolutional Networks, and/or Conventional ANNs. AI and ML technologies are developing in many ways and so the rigorous definitions are still developing. This means that: (i) existing textbooks are outdated and so cannot offer efficient strategies demanded by industry and academy, and (ii) textbooks nowadays are not interactive as online tutorials provided, for example, by Google Colab. The above listed four strategies are new cutting-edge ways to the optimisation task, supported with many tutorials available online.
Example of Optimisation Solution
An example of an ANN optimisation in MATLAB is presented by a conference paper published by the Computer Science students in Springer proceedings. Other solutions will be discussed.
Attachment:- Concepts and Technologies of Artificial Intelligence.rar