Search
Now showing items 11-20 of 119
Improving end-to-end neural network models for low-resource automatic speech recognition
(Massachusetts Institute of Technology, 2020)
In this thesis, we explore the problem of training end-to-end neural network models for automatic speech recognition (ASR) when limited training data are available. End-to-end models are theoretically well-suited to ...
Spintronics using low magnetization materials
(Massachusetts Institute of Technology, 2020)
Information storage using magnetic materials is accomplished by controlling and sensing the magnetic moment orientation of nanoscale ferromagnets. In order to improve performance and compete with existing and alternative ...
Graph guided predictions
(Massachusetts Institute of Technology, 2020)
Graphs provide a natural abstraction to model relational and strategic data in domains as diverse as biology (e.g., molecules), multiagent settings (e.g., online vendors on ecommerce platforms), and distributed systems ...
A unified modeling for control of reactive power dynamics in electrical energy systems
(Massachusetts Institute of Technology, 2020)
This thesis is motivated by the renewed need to understand and control the dynamics of reactive power in the electrical energy systems. Of particular interest are the dynamical non-sinusoidal interactions between heterogeneous ...
A design methodology for computer architecture parameterized by robot morphology
(Massachusetts Institute of Technology, 2020)
Robots that safely interact with people are a promising solution to address societal challenges from elder care to hazardous work environments. A key computational barrier to the robust autonomous operation of complex ...
Efficient metric representations for big data
(Massachusetts Institute of Technology, 2020)
Contemporary datasets are often represented as points in a high-dimensional metric space. To deal with increasingly larger datasets, many algorithms rely on efficient or compressed representations of the induced metric. ...
Programming technologies for engineering quality multicore software
(Massachusetts Institute of Technology, 2020)
The widespread availability of large multicore computers in the cloud has given engineers and scientists unprecedented access to large computing platforms. Traditionally, high-end computing solutions have been developed ...
Network system optimization with reinforcement learning : methods and applications
(Massachusetts Institute of Technology, 2020)
Networked systems rely on many control and decision-making algorithms. Classical approaches to designing and optimizing these algorithms, developed over the last four decades, are poorly suited to the diverse and demanding ...
Developing clinically useful risk stratification models
(Massachusetts Institute of Technology, 2020)
When a patient presents to a hospital with symptoms of cardiovascular disease, one of the first courses of action is to estimate the patient's risk of an adverse outcome. The process of categorizing patients by risk level, ...
Towards automated construction of compiler optimizations
(Massachusetts Institute of Technology, 2020)
Compilers are the workhorse that bridge the gap between human-readable and machine-executable code.e ultimate goal of a compiler is to find a legal translation that provides the most optimized machine code sequence for a ...