Projects per year
Abstract
The AI community has been paying attention to submodular functions due to their various applications (e.g., target search and 3D mapping). Learning submodular functions is a challenge since the number of a function’s outcomes of N sets is 2^{N} . The stateoftheart approach is based on compressed sensing techniques, which are to learn submodular functions in the Fourier domain and then recover the submodular functions in the spatial domain. However, the number of Fourier bases is relevant to the number of sets’ sensing overlapping. To overcome this issue, this research proposed a submodular deep compressed sensing (SDCS) approach to learning submodular functions. The algorithm consists of learning autoencoder networks and Fourier coefficients. The learned networks can be applied to predict 2^{N} values of submodular functions. Experiments conducted with this approach demonstrate that the algorithm is more efficient than the benchmark approach.
Original language  English 

Article number  2591 
Journal  Sensors (Switzerland) 
Volume  20 
Issue number  9 
DOIs  
State  Published  1 May 2020 
Keywords
 Autoencoder
 Compressed sensing
 Deep learning
 Submodularity
Fingerprint
Dive into the research topics of 'Deep compressed sensing for learning submodular functions'. Together they form a unique fingerprint.Projects
 2 Finished

Deep Inverse Reinforcement Learning for Informative Path Planning(1/3)
1/08/19 → 31/07/20
Project: Research
