The final project contains 5 parts. The paper must be submitted using the templates of the IEEE Transactions on Computers. You will be graded on formatting.
The writeups should be cumulative: the writeup for part 2 should be added to the end of the writeup for part 1, and so on. Each part should be no more than 1 page of text, not counting figures, tables, titles and bibliography.
Grading of paper is based on scientific correctness (are all of your statements backed up by citations and/or by your own experiments?), clarity (is your language and formatting clear?), and creativity (have you chosen an interesting problem, and an interesting way to try to solve it?). For more information about how to write technical papers, see, for example, the IEEE Write Your Paper page.
Components of the Final Project:
- Intro: choose a problem; say why it’s interesting
- Background: review three papers that studied your problem
- Propose an algorithm that does something relevant for your problem, describe the algorithm clearly, and describe why the algorithm might work
- Run an experiment. Describe experimental methods (dataset and performance metric) and results
- Discuss the degree to which your experimental result is a success, a failure, or uninterpretable. In light of your experiment, and of the papers you reviewed, discuss possible next steps
What to write about:
In general, you should pick an area that interests you. But you might ask, what are the “areas”? There are at least three ways to divide AI into topic areas.
- Different definitions of intelligence. So, for example, some areas of AI focus on making a computer more rational (planning, reasoning). Some focus on making a computer more human-like (natural language processing, emotion). Some focus on making a computer more autonomous (sensors of all kinds, robustness to error).
- PEAS: Performance (e.g., methods for optimization, methods for measuring performance, generalization error, computational considerations), Environment (agents on the internet, agents who interact with humans, robots who interact with humans, delivery drones, robots in environments where a human could never go), Actuators (hardware issues, configuration space of a robot, path planning, reinforcement learning), Sensors (audio, ultrasound, vision, infrared, 3d vision, radar, wifi, biomedical sensors, seismic sensors, mapping).
- Application area: data science, biomedical imaging, automatic medical diagnosis, speech recognition, spoken-language translation, automatic story generation, purposive dialog agents, chat, automatic advertising, automatic topic detection, named entity recognition, syntactic parsing, data mining, fraud detection, anomaly detection, conflict resolution, genomics, preoteomics, scientific inference, automatic image generation, image style transfer, synthetic singing, automatic music composition
Here’s a highly biased and under-representative Venn diagram of some of the possible topics you could choose:
Places to look for relevant papers:
Major conferences
Here is a list of some major conferences that you can scan to find more information about some of the topics suggested above.
- Core AI
- AAAI, IJCAI
- Computer vision
- CVPR, ICCV, ECCV
- Natural language
- ACL, NAACL, EACL, EMNLP, COLING (All available at the ACL anthology web site.)
- Speech
- ICASSP, Interspeech
- Machine Learning
- NIPS, ICML, ICLR
- Robotics
- ICRA, IROS
