#### Filter Results:

- Full text PDF available (8)

#### Publication Year

2008

2017

- This year (0)
- Last 5 years (16)
- Last 10 years (24)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Michael Fairbank
- The 2012 International Joint Conference on Neuralâ€¦
- 2012

We describe an Adaptive Dynamic Programming algorithm VGL(Î») for learning a critic function over a large continuous state space. The algorithm, which requires a learned model of the environment,â€¦ (More)

- Michael Fairbank, Eduardo Alonso, Danil V. Prokhorov
- IEEE Transactions on Neural Networks and Learningâ€¦
- 2012

We derive an algorithm to exactly calculate the mixed second-order derivatives of a neural network's output with respect to its input vector and weight vector. This is necessary for the adaptiveâ€¦ (More)

- Michael Fairbank, Shuhui Li, Xingang Fu, Eduardo Alonso, Donald C. Wunsch
- Neural Networks
- 2014

We present a recurrent neural-network (RNN) controller designed to solve the tracking problem for control systems. We demonstrate that a major difficulty in training any RNN is the problem ofâ€¦ (More)

- Shuhui Li, Donald C. Wunsch, Michael Fairbank, Eduardo Alonso
- The 2012 International Joint Conference on Neuralâ€¦
- 2012

Three-phase grid-connected converters are widely used in renewable and electric power system applications. Traditionally, grid-connected converters are controlled with standard decoupled d-q vectorâ€¦ (More)

- Xingang Fu, Shuhui Li, Michael Fairbank, Donald C. Wunsch, Eduardo Alonso
- IEEE Transactions on Neural Networks and Learningâ€¦
- 2015

This paper investigates how to train a recurrent neural network (RNN) using the Levenberg-Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected converter (GCC)â€¦ (More)

- Michael Fairbank, Eduardo Alonso
- ArXiv
- 2011

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a largeâ€¦ (More)

- Michael Fairbank, Eduardo Alonso
- The 2012 International Joint Conference on Neuralâ€¦
- 2012

This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the valueâ€¦ (More)

- Jialin Liu, Michael Fairbank, Diego Perez Liebana, Simon M. Lucas
- ArXiv
- 2016

The OneMax problem is a standard benchmark optimisation problem for a binary search space. Recent work on applying a Bandit-Based Random Mutation Hill-Climbing algorithm to the noisy OneMax problemâ€¦ (More)

- Spyridon Samothrakis, Tom Vodopivec, Michael Fairbank, Maria Fasli
- IJCAI
- 2017

In this paper, we present a simple, yet effective, attention and memory mechanism that is reminiscent of Memory Networks and we demonstrate it in question-answering scenarios. Our mechanism is basedâ€¦ (More)

- Shuhui Li, Xingang Fu, Ishan Jaithwa, Eduardo Alonso, Michael Fairbank, Donald C. Wunsch
- 2015 7th International Joint Conference onâ€¦
- 2015

A microgrid consists of a variety of inverter-interfaced distributed energy resources (DERs). A key issue is how to control DERs within the microgrid and how to connect them to or disconnect themâ€¦ (More)