M. M. Hassan Mahmud

Learn More
In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have been used successfully in practice and PAC analysis of these methods have been developed. But the key notion of relatedness between tasks has not yet been defined clearly, which(More)
Different interfaces allow a user to achieve the same end goal through different action sequences, e.g., command lines vs. drop down menus. Interface efficiency can be described in terms of a cost incurred, e.g., time taken, by the user in typical tasks. Realistic users arrive at evaluations of efficiency, hence making choices about which interface to use,(More)
We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement learning. This is necessary when the number of previous tasks is large and the cost of measuring similarity counteracts the(More)
In this paper we introduce the MDP-with-agents model for addressing a particular sub-class of non-stationary environments where the learner is required to interact with other agents. The behavior-policies of the agents are determined by a latent variable that changes rarely, but can modify the agent policies drastically when it does change (like traffic(More)
  • Moin Mahmud, Tanvee Shaikh, Jeeshan Kabeer, Tareque Mohmud, Chowdhury Asif, Ahmed Sarja +2 others
  • 2013
The rapid development of bioinformatics has resulted in the explosion of DNA sequence data which is characterized by large number of items. Studies have shown that biological functions are dictated by contagious portions of the DNA sequence. Finding contiguous frequent patterns from long data sequences such as DNA sequences is a particularly challenging(More)
  • 1