Post-grad AI & AI programming coursework, neural network training and evaluation. Achieved 88%
Go to file
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.

  1. Evaluate the network's tendency to overfit by varying the number of epochs and hidden layers being used
  2. Multiple classifier performance using majority vote
  3. Repeat 2 with two different optimisers (trainlm, trainrp)
  4. Extension: Distinguish between two equi-probable classes of overlapping 2D Gaussians