Search
Now showing items 1-10 of 32
Feature Factory : a collaborative, crowd-sourced machine learning system
(Massachusetts Institute of Technology, 2015)
In this thesis, I designed, implemented, and tested a machine learning learning system designed to crowd-source feature discovery called Feature Factory. Feature Factory provides a complete web-based platform for users to ...
A flexible framework for composing end to end machine learning pipelines
(Massachusetts Institute of Technology, 2018)
In this thesis, we aim to simplify the building of end-to-end machine learning pipelines while preserving the performance of such pipelines on real data. As a solution to this, we propose the MLBlocks framework, a system ...
Solving Dec-MDPs with options and intention recognition
(Massachusetts Institute of Technology, 2016)
In this thesis, we designed and implemented an algorithm to find approximate solutions to multi-agent systems. We model the problems with a Decentralized Markov Decision Process, and we make use of options and intention ...
Not a zero sum game : how to simultaneously maximize efficiency and privacy in data-driven urban governance
(Massachusetts Institute of Technology, 2019)
India has been striving towards digitization of citizen data and government services using e-governance platforms to improve accountability, transparency, and efficiency. Accordingly, India launched the world's largest ...
Generating and adjudicating digital legal agreements using Ethereum smart contracts
(Massachusetts Institute of Technology, 2019)
Across the world, countless legal agreements are drafted, signed, and disputed every day. In most cases, the drafting process consists of costly and lengthy revisions of paper-based legal agreements. Furthermore, once ...
An ethereum-based, integrity-first communication protocol for IoT devices
(Massachusetts Institute of Technology, 2019)
The use of IoT devices in smart cities, advanced energy delivery systems, manufacturing plants and transportation systems is rapidly increasing. These systems are often responsible for communicating critical data about ...
Cooperate to compete : composable planning and inference in multi-agent reinforcement learning
(Massachusetts Institute of Technology, 2018)
Cooperation within a competitive social situation is a essential part of human social life. This requires knowledge of teams and goals as well as an ability to infer the intentions of both teammates and opponents from ...
Scalable fault tolerance for high-performance streaming dataflow
(Massachusetts Institute of Technology, 2019)
Streaming dataflow systems offer an appealing alternative to classic MySQL / memcached web backend stacks. But websites must not go down, and current fault tolerance techniques for dataflow systems either come with long ...
State estimation for manipulation with compliance control and force sensing
(Massachusetts Institute of Technology, 2016)
This thesis investigates implementation details for a simple robotic manipulation domain. The configuration space of the domain is discretized and factored into contact states and metric states. A low-level force and ...
Image Miner : an architecture to support deep mining of images
(Massachusetts Institute of Technology, 2015)
In this thesis, I designed a cloud based system, called ImageMiner, to tune parameters of feature extraction process in a machine learning pipeline for images. Feature extraction is a key component of the machine learning ...