Page 114 |
Save page Remove page | Previous | 114 of 151 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
gradient computation into the gradient of the loss network with respect to predictions of model
f (x) times the gradient of model f with respect to model parameters†,
© M (y; f (x)) = ©fM (y; f (x))© f (x): (5.4)
Once we have updated the model parameters new = − © Llearned using the current meta-loss
network parameters , we want to measure how much learning progress has been made with
loss-parameters and optimize via gradient descent. Note, that the new model parameters new
are implicitly a function of loss-parameters , because changing would lead to different new. In
order to evaluate new, and through that loss-parameters , we introduce the notion of a task-loss
during meta-train time. For instance, we use the mean-squared-error (MSE) loss, which is typically
used for regression tasks, as a task-loss LT = (y − f new(x))2. We now optimize loss parameters
by taking the gradient of LT with respect to as follows†:
© LT = ©fLT © newf new© new = ©fLT © newf new© [ − © E M (y; f (x)) (5.5)
where we first apply the chain rule and show that the gradient with respect to the meta-loss
parameters requires the new model parameters new. We expand new as one gradient step on
based on meta-lossM , making the dependence on explicit.
Optimization of the loss-parameters can either happen after each inner gradient step (where
inner refers to using the current loss parameters to update ), or after M inner gradient steps with
the current meta-loss networkM .
The latter option requires back-propagation through a chain of all optimizee update steps.
In practice we notice that updating the meta-parameters after each inner gradient update step
†Alternatively this gradient computation can be performed using automatic differentiation
99
Object Description
| Title | Data scarcity in robotics: leveraging structural priors and representation learning |
| Author | Molchanov, Artem |
| Author email | a.molchanov86@gmail.com;molchano@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2020-05-11 |
| Date submitted | 2020-08-11 |
| Date approved | 2020-08-11 |
| Restricted until | 2020-08-11 |
| Date published | 2020-08-11 |
| Advisor (committee chair) | Sukhatme, Gaurav Suhas |
| Advisor (committee member) |
Ayanian, Nora Culbertson, Heather Gupta, Satyandra K. |
| Abstract | Recent advances in Artificial Intelligence have benefited significantly from access to large pools of data accompanied in many cases by labels, ground truth values, or perfect demonstrations. In robotics, however, such data are scarce or absent completely. Overcoming this issue is a major barrier to move robots from structured laboratory settings to the unstructured real world. In this dissertation, by leveraging structural priors and representation learning, we provide several solutions when data required to operate robotics systems is scarce or absent. ❧ In the first part of this dissertation we study sensory feedback scarcity. We show how to use high-dimensional alternative sensory modalities to extract data when primary sensory sources are absent. In a robot grasping setting, we address the problem of contact localization and solve it using multi-modal tactile feedback as the alternative source of information. We leverage multiple tactile modalities provided by electrodes and hydro-acoustic sensors to structure the problem as spatio-temporal inference. We employ the representational power of neural networks to acquire the complex mapping between tactile sensors and the contact locations. We also investigate scarce feedback due to the high cost of measurements. We study this problem in a challenging field robotics setting where multiple severely underactuated aquatic vehicles need to be coordinated. We show how to leverage collaboration among the vehicles and the spatio-temporal smoothness of the ocean currents as a prior to densify feedback about ocean currents in order to acquire better controllability. ❧ In the second part of this dissertation, we investigate scarcity of the data related to the desired task. We develop a method to efficiently leverage simulated dynamics priors to perform sim-to-real transfer of a control policy when no data about the target system is available. We investigate this problem in the scenario of sim-to-real transfer of low-level stabilizing quadrotor control policies. We demonstrate that we can learn robust policies in simulation and transfer them to the real system while acquiring no samples from the real quadrotor. Finally, we consider the general problem of learning a model with a very limited number of samples using meta-learned losses. We show how such losses can encode a prior structure about families of tasks to create well-behaved loss landscapes for efficient model optimization. We demonstrate the efficiency of our approach for learning policies and dynamics models in multiple robotics settings. |
| Keyword | robotics; machine learning; artificial intelligence |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Provenance | Electronically uploaded by the author |
| Type | texts |
| Legacy record ID | usctheses-m |
| Contributing entity | University of Southern California |
| Rights | Molchanov, Artem |
| Physical access | The author retains rights to his/her dissertation, thesis or other graduate work according to U.S. copyright law. Electronic access is being provided by the USC Libraries in agreement with the author, as the original true and official version of the work, but does not grant the reader permission to use the work if the desired use is covered by copyright. It is the author, as rights holder, who must provide use permission if such use is covered by copyright. The original signature page accompanying the original submission of the work to the USC Libraries is retained by the USC Libraries and a copy of it may be obtained by authorized requesters contacting the repository e-mail address given. |
| Repository name | University of Southern California Digital Library |
| Repository address | USC Digital Library, University of Southern California, University Park Campus MC 7002, 106 University Village, Los Angeles, California 90089-7002, USA |
| Repository email | cisadmin@lib.usc.edu |
| Filename | etd-MolchanovA-8923.pdf |
| Archival file | Volume13/etd-MolchanovA-8923.pdf |
Description
| Title | Page 114 |
| Full text | gradient computation into the gradient of the loss network with respect to predictions of model f (x) times the gradient of model f with respect to model parameters†, © M (y; f (x)) = ©fM (y; f (x))© f (x): (5.4) Once we have updated the model parameters new = − © Llearned using the current meta-loss network parameters , we want to measure how much learning progress has been made with loss-parameters and optimize via gradient descent. Note, that the new model parameters new are implicitly a function of loss-parameters , because changing would lead to different new. In order to evaluate new, and through that loss-parameters , we introduce the notion of a task-loss during meta-train time. For instance, we use the mean-squared-error (MSE) loss, which is typically used for regression tasks, as a task-loss LT = (y − f new(x))2. We now optimize loss parameters by taking the gradient of LT with respect to as follows†: © LT = ©fLT © newf new© new = ©fLT © newf new© [ − © E M (y; f (x)) (5.5) where we first apply the chain rule and show that the gradient with respect to the meta-loss parameters requires the new model parameters new. We expand new as one gradient step on based on meta-lossM , making the dependence on explicit. Optimization of the loss-parameters can either happen after each inner gradient step (where inner refers to using the current loss parameters to update ), or after M inner gradient steps with the current meta-loss networkM . The latter option requires back-propagation through a chain of all optimizee update steps. In practice we notice that updating the meta-parameters after each inner gradient update step †Alternatively this gradient computation can be performed using automatic differentiation 99 |
