Post-grad AI & AI programming coursework, neural network training and evaluation. Achieved 88%
graphs | ||
matlab | ||
report | ||
results | ||
.gitattributes | ||
.gitignore | ||
features.csv | ||
nbgen | ||
nncw.ipynb | ||
nncw.py | ||
README.md | ||
scratchpad.ipynb | ||
targets.csv |
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