Post-grad AI & AI programming coursework, neural network training and evaluation. Achieved 88%
|
2021-03-21 09:56:27 +00:00 |
graphs
|
pickling results, plotting from dataset only
|
2021-03-21 09:56:27 +00:00 |
matlab
|
template MatLab script from nnstart, saved dataset to csv for possible py use
|
2021-03-02 19:21:47 +00:00 |
report
|
added template tensorflow notebook, added skeleton report
|
2021-03-02 23:06:09 +00:00 |
results
|
pickling results, plotting from dataset only
|
2021-03-21 09:56:27 +00:00 |
.gitattributes
|
Initial commit
|
2021-03-02 19:05:45 +00:00 |
.gitignore
|
added template tensorflow notebook, added skeleton report
|
2021-03-02 23:06:09 +00:00 |
features.csv
|
template MatLab script from nnstart, saved dataset to csv for possible py use
|
2021-03-02 19:21:47 +00:00 |
nncw.ipynb
|
pickling results, plotting from dataset only
|
2021-03-21 09:56:27 +00:00 |
README.md
|
exp2 draft, exporting results
|
2021-03-19 17:21:00 +00:00 |
scratchpad.ipynb
|
pickling results, plotting from dataset only
|
2021-03-21 09:56:27 +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
.
- 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