Some Results
We have done simulations with our model on the actual data. The data is pretty noisy since it has been collected manually by researchers on the ground. The initial results though are encouraging. We now have some idea of the preferences of the herders as we have recovered the underlying reward function. The next step [...]
Model Description
We have considered two kinds of models for the MDP. In the first model we have modeled the state space as grid world. Each cell on the grid world represents a particular geographical location of size 0.1 degree in latitude and 0.1 degree in longitude. The action space is based on actions taken each day [...]
Approach to the Problem (IRL)
The technical challenge is that herd movement is a large and complex dynamic discrete choice problem: pastoralists must decide which particular water points to move to, as a function of a large and complex state space. Application of the typical econometric modeling techniques from economics would seem to run into two immediate challenges: (i) the [...]
Pastoralist Problem and Collaboration with Cornell’s Applied Economics department
Background on Pastoralist Problem Our applied problem is centered on explaining the movement over time and space of animal herds in the arid and semi-arid lands of Northern Kenya. In this region crop agriculture is difficult, and hence pastoralists (animal herders) have adopted the livelihood strategy of managing large livestock herds (camels, cattle, sheep, and [...]
Introduction to Pastoral Systems
My project is to develop models for understanding and predicting decisions taken by pastoral (animal herders) communities in response to changes in Nature and their environment. The subjects of the study are East African pastoralists who have biannual dry seasons and need to migrate due to it. A survey was collected by the USAID Global [...]
BOOM Award for ICS Social Network Discovery Project
This past semester, Karan Kurani and Jason Marcell were presented with the 2011 EMC Big Data Award at Cornell’s BOOM 2011.
Update on Multi-view Ensemble Learning
Hello World. Its been a long time since the last blog post. I (Karan Kurani) have been working with Dr Theodoros Damoulas and Aurelie Harou over the last 3 months to build upon the work mentioned in the last 2 posts. I was side tracked from this project for a little while by working on [...]
mRVM Progress
Work on the mRVM classifier is coming along steadily. This past weekend I played with the following new tools:
Chef
Vagrant
Valgrind
Using Hibernate for the Social Network Discovery Project
As the first step of our Social Network Discovery project, we wanted to pull down a bunch of data from some data sources where we could massage it and filter it before it went on it’s way to the next step in the process. We chose to store our data in a MySQL database and [...]
Multi-Kernel Relevance Vector Machines
Bayesian classi?cation algorithms, the multi-class multi-kernel Relevance Vector Ma- chines (mRVMs) that have been recently proposed. Since this is a multi-author blog and this is my first contribution, I will start by introducing myself. My name is Jason Marcell. I am a CS Masters student working under the supervision of Dr. Theodoros Damoulas. My primary [...]
keep looking »
Recent Comments