Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Assignments from Neil #11

Open
wants to merge 30 commits into
base: gh-pages
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
30 commits
Select commit Hold shift + click to select a range
f5c1caa
Create hello-world notebook, fill with background information
skipperguy12 Jul 12, 2016
c483157
Create explications response
skipperguy12 Jul 12, 2016
5aacdde
Implement SM check method, complete email SM and tests
skipperguy12 Jul 13, 2016
4d5feb2
Modify email checking, finish DFS on paths
skipperguy12 Jul 13, 2016
a6db5b4
Add a code cell into hello world with a simple environment test
skipperguy12 Jul 13, 2016
2f3d7e5
Merge branch 'gh-pages' of https://github.com/JoeOsborn/spcs-ai into …
skipperguy12 Jul 14, 2016
e15320d
Temporary work
skipperguy12 Jul 14, 2016
9a2b089
Extract correct coordinates
skipperguy12 Jul 14, 2016
91fa078
Update Maze Solvers
skipperguy12 Jul 14, 2016
fc5d075
Finish assignment 1 of Maze Solvers for the most part
skipperguy12 Jul 15, 2016
e20f017
Code cleanup and refactor, readd other mazes. Broken for maze2
skipperguy12 Jul 15, 2016
e0f37f4
Move work to named file, readd original Maze Solvers file to prevent …
skipperguy12 Jul 15, 2016
136a32c
Fix maze2 issues involving free checking
skipperguy12 Jul 15, 2016
1d6150d
Merge branch 'gh-pages' of https://github.com/JoeOsborn/spcs-ai into …
skipperguy12 Jul 15, 2016
ffb8a3b
Store maze changes instead of coordinates, implement switch handling
skipperguy12 Jul 15, 2016
b12be29
Fix error
skipperguy12 Jul 15, 2016
378059f
test
skipperguy12 Jul 15, 2016
829b77a
Revert test
skipperguy12 Jul 15, 2016
a80c00c
Remove a lot of debug, finish. IT WORKS! WE'RE DONE.
skipperguy12 Jul 15, 2016
13a3885
Comment debug (again?)
skipperguy12 Jul 15, 2016
59561d0
Merge branch 'gh-pages' of https://github.com/JoeOsborn/spcs-ai into …
skipperguy12 Jul 16, 2016
1e61d70
Temporary work
skipperguy12 Jul 16, 2016
3ba738d
Even closer, use maze instances and store cost + path inside maze object
skipperguy12 Jul 16, 2016
432eaf7
Add some untested stuff
skipperguy12 Jul 17, 2016
9214bb4
Finish project ideas
skipperguy12 Jul 18, 2016
1ce95ad
Finished assignment 1, thanks @kennyng
skipperguy12 Jul 18, 2016
87fac3c
Add solution to maze4
skipperguy12 Jul 18, 2016
00fa150
Merge branch 'gh-pages' of https://github.com/JoeOsborn/spcs-ai into …
skipperguy12 Jul 20, 2016
a02ab54
Finish assignment
skipperguy12 Jul 20, 2016
2d570a7
Follow machinelearningmastery tutorial on keras for simple ANN
skipperguy12 Jul 21, 2016
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions projects/1-explications/neil.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# The Google Self Driving Car
Google's self driving cars are developed by Google X, and are impressive autonomous vehicles which operate in line with the rules of the road. They intelligently interpret their environment and react to them by steering, accelerating, or decelerating.

The project was formerly led by Sebastian Thrun, and is developed by a team of Google engineers. It is simply an attempt to advance autonomous vehicles, and Google X is a good place to lead this research because their labs are dedicated to trying projects which at some point were considered impossible.

## Knowledge Representation
The Google Car utilizes expensive sensors to generate a 3D view of the world around it. It utilizes this information to form multiple data models of where pedestrians around it are.

Central concepts based off released information is the car's location, at all times. The team has made it clear that GPS is too inaccurate for their purposes, so it combines data from GPS and it's laser sensor to precisely determine location.

Other, more peripheral information, is likely information that it filters out. This probably includes objects on the sidewalk (such as people, dogs, people in vehicles, etc) which it predicts are not going to affect it's driving abilities.

## Interaction With Humans
The car is designed to be used by human passengers, and is meant to avoid hitting other objects while efficiently moving the passenger from point A to point B. It assumes that the human will not try to do anything in the car to alter the driving (latest revisions of the car do not include steering wheel or pedals), and it also assumes that the human will be content with preset rules of the car (max speed, route, etc).


### Malicious User Interaction
A hostile user could probably try to damage the car and steal one of the sensors (which are extremely expensive), or possibly try to weigh down the car and mess with its expectations. To injure others, a user might be able to take control of the vehicle using a steering wheel and override a decision made by the Google car. Indeed, Google claims that a few of it's accidents were caused by the driver, not the car itself. This isn't anything more than manually causing harm, but it raises doubt on the accuracy of autonomous vehicles. A hostile user from outside the car could do something that it has never experienced (and thus cannot react to), such as jumping from the sidewalk in front of the car, taping a sensor while it's stopped, or trying to drive head on into the Google car. I doubt that the Google car is prepared for any of these cases (except possibly a malfunctioning sensor).
79 changes: 79 additions & 0 deletions projects/1-hello-world/neil.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1,79 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"# Introduction\n",
"Hello, my name is Neil. \n",
"## Background In Programming and AI\n",
"I've been into programming for a about 6-7 years now. I started off with copying tutorials line by line. I don't know which language or what I made exactly, I just recall following Youtube tutorials for hours. Then I moved onto Java, making plugins for a game (Minecraft). I slowly became more proficient with it, and eventually took AP Computer Science and got a 5. I learned a lot by trying (and usually failing) in attempting to make projects/networks with friends, and intend to be a programmer in the future as a career choice.\n",
"\n",
"As for AI, I got interested in it over the summer last year, and chose it for my Math Research. I explored the very basics of ML, creating a linear regression using gradient descent (simple, but at least it's simple enough for me to verify). I made it such that I could easily expand it later into multiple dimensions. I also created a basic genetic algorithm in Java, and have played with some Python libraries to make a basic neural network. \n",
"\n",
"\n",
"## What I Hope to Gain From This Course\n",
"I hope to become more familiar with using the various tools in ML/AI, rather than implementing them by hand. I did that for my research, and it was not fun (especially with it only accomplishing something as simple as linreg).\n",
"\n",
"I also hope to gain some inspiration for my next year research project, which is going to be ML/AI applied to some field of science. I currently am looking for an idea which is novel and will be genuinely interesting to look into.\n",
"\n",
"\n",
"## Favorite Hobbies Outside of Programming (and computing)\n",
"I like playing videogames. A lot. I have over 1000 hours in Counter Strike: Global Offensive, and recently started playing Overwatch.\n",
"\n",
"Outside of computers completely, I enjoy badminton and watching movies with friends. "
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n"
]
}
],
"source": [
"print(1==1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Loading