Post-grad AI & AI programming coursework, neural network training and evaluation. Achieved 88%
|
|
2021-04-06 21:15:26 +01:00 |
|
graphs
|
began writing report, added nbconvert script
|
2021-04-06 21:15:26 +01:00 |
|
matlab
|
template MatLab script from nnstart, saved dataset to csv for possible py use
|
2021-03-02 19:21:47 +00:00 |
|
report
|
began writing report, added nbconvert script
|
2021-04-06 21:15:26 +01:00 |
|
results
|
variable nodes exp2, graph exports
|
2021-04-06 17:29:15 +01:00 |
|
.gitattributes
|
Initial commit
|
2021-03-02 19:05:45 +00:00 |
|
.gitignore
|
began writing report, added nbconvert script
|
2021-04-06 21:15:26 +01:00 |
|
features.csv
|
template MatLab script from nnstart, saved dataset to csv for possible py use
|
2021-03-02 19:21:47 +00:00 |
|
nbgen
|
began writing report, added nbconvert script
|
2021-04-06 21:15:26 +01:00 |
|
nncw.ipynb
|
variable nodes exp2, graph exports
|
2021-04-06 17:29:15 +01:00 |
|
nncw.py
|
added generated script to report, removed non-UTF-8 chars
|
2021-03-29 19:17:14 +01:00 |
|
README.md
|
interrim feedback
|
2021-03-22 20:49:29 +00:00 |
|
scratchpad.ipynb
|
exp2 agreement, individual accuracy
|
2021-03-26 20:01:05 +00:00 |
|
targets.csv
|
template MatLab script from nnstart, saved dataset to csv for possible py use
|
2021-03-02 19:21:47 +00:00 |
Shallow Neural Network Training Coursework
Evaluating a neural network using the MatLab cancer_dataset. Development contained in the nncw.ipynb notebook.
- Evaluate the network's tendency to overfit by varying the number of epochs and hidden layers being used
- Multiple classifier performance using majority vote
- Repeat 2 with two different optimisers (
trainlm, trainrp)
- Extension: Distinguish between two equi-probable classes of overlapping 2D Gaussians
