2018 case study: Difference between revisions
Mr. MacKenty (talk | contribs) |
Mr. MacKenty (talk | contribs) |
||
| Line 31: | Line 31: | ||
* [[Multi-layer perceptron (MLP)]] | * [[Multi-layer perceptron (MLP)]] | ||
* [[Nearest neighbour algorithm ]] | * [[Nearest neighbour algorithm ]] | ||
* [[Neural networks]] | |||
* [[Overfitting]] | * [[Overfitting]] | ||
* [[Point clouds]] | * [[Point clouds]] | ||
Revision as of 06:31, 13 March 2018
Case study[1]
Introduction[edit]
This page will help you organize and understand the 2018 case study.
The case study[edit]
Click here for the full pdf case study
Terms worth deeply understanding[edit]
These articles have been written by students. Any article with a green checkmark 
has been approved by a teacher and can be used reliably to study.
- Template for student-defined terms
- Autonomous
- Backpropagation
- BigO notation
- Bounding boxes
- Brute-force
- Convolutional neural networks (CNNs)
- Cost function
- Deep learning
- Dijkstra’s algorithm
- End-to-end learning
- Feature maps (Activation maps)
- Filters (Kernels)
- Filter stride
- Greedy algorithm
- Machine learning
- Max-pooling / Pooling
- Multi-layer perceptron (MLP)
- Nearest neighbour algorithm
- Neural networks
- Overfitting
- Point clouds
- Receptive field
- Sensor Fusion
- Society of Automotive Engineers
- Shift invariance (Spatial invariance)
- Vehicle-to-vehicle (VTV) protocol
- Vehicle-to-infrastructure (VTI) protocol
Previous years case study[edit]
- Click here for 2017 case study wiki-notes
- Click here for the 2017 case study
- Click here for the 2016 case study