Abstract | ||
---|---|---|
A promising approach to autonomous driving is machine learning. In such systems, training datasets are created that capture the sensory input to a vehicle as well as the desired response. A disadvantage of using a learned navigation system is that the learning process itself may require a huge number of training examples and a large amount of computing. To avoid the need to collect a large training set of driving examples, we describe a system that takes advantage of the huge number of training examples provided by ImageNet, but is able to adapt quickly using a small training set for the specific driving environment. |
Year | Venue | Field |
---|---|---|
2016 | arXiv: Robotics | Training set,Simulation,Incremental learning,Navigation system,Artificial intelligence,Engineering,Robot,Disadvantage,Machine learning |
DocType | Volume | Citations |
Journal | abs/1606.08057 | 0 |
PageRank | References | Authors |
0.34 | 1 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Artem Provodin | 1 | 0 | 0.34 |
Liila Torabi | 2 | 22 | 1.27 |
Beat Flepp | 3 | 253 | 10.85 |
Yann LeCun | 4 | 26090 | 3771.21 |
Michael Sergio | 5 | 0 | 0.34 |
Lawrence D. Jackel | 6 | 935 | 777.80 |
Urs Muller | 7 | 389 | 24.17 |
Jure Zbontar | 8 | 119 | 6.96 |