diff --git a/README.md b/README.md index 6d6383dcee77f8cf092b4b7a98f8fb176ce9deb1..a9e1c100dfa2fe9a185aec2183daece553c67cbd 100644 --- a/README.md +++ b/README.md @@ -24,10 +24,60 @@ Here we can conclude that the best K is 5, (if we don't use k = 1) with a perfo ### Maths 1° + + +2° + + + +3° + + + +4° + + + +5° + + + +6° + + + +7° + + + +8° + + + +9° + + + + + ### Code +All the code can be found in the Python file mlp.py. + +Below, you will find the graph of accuracy as a function of the number of epochs. We used a learning rate of 0.1 and a split ratio of 0.9 between the training and testing datasets. + + + + + +Firstly, we observe that accuracy increases with each epoch. + +However, after 100 epochs, the accuracy is around 16.2%, which is about half the accuracy achieved by the KNN method. + +In conclusion, the MLP method is somewhat disappointing. It might be improved by increasing the number of epochs or adjusting the learning rate. I also observed that the MLP method was faster than the KNN method. + diff --git a/mlp.png b/mlp.png deleted file mode 100644 index 83352343a69a7879686c6ac19c0816b071697b1d..0000000000000000000000000000000000000000 Binary files a/mlp.png and /dev/null differ diff --git a/mlp_maths/.gitkeep b/mlp_maths/.gitkeep new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/mlp_maths/q1.PNG b/mlp_maths/q1.PNG new file mode 100644 index 0000000000000000000000000000000000000000..f09034cf83cf056022a0d8e084b7794ec36af8af Binary files /dev/null and b/mlp_maths/q1.PNG differ diff --git a/mlp_maths/q2.PNG b/mlp_maths/q2.PNG new file mode 100644 index 0000000000000000000000000000000000000000..2060c4e6df8dcd1ecffb45e3323f401599d7ecd8 Binary files /dev/null and b/mlp_maths/q2.PNG differ diff --git a/mlp_maths/q3.PNG b/mlp_maths/q3.PNG new file mode 100644 index 0000000000000000000000000000000000000000..092857da2ce67dc19216854bffe58467d3b257e0 Binary files /dev/null and b/mlp_maths/q3.PNG differ diff --git a/mlp_maths/q4.PNG b/mlp_maths/q4.PNG new file mode 100644 index 0000000000000000000000000000000000000000..821c1fcca898c3d56cd4c183b8895cd309a54e39 Binary files /dev/null and b/mlp_maths/q4.PNG differ diff --git a/mlp_maths/q5.PNG b/mlp_maths/q5.PNG new file mode 100644 index 0000000000000000000000000000000000000000..3a6cf39ede6e7a6224f7a816bed96e033100a84b Binary files /dev/null and b/mlp_maths/q5.PNG differ diff --git a/mlp_maths/q6.PNG b/mlp_maths/q6.PNG new file mode 100644 index 0000000000000000000000000000000000000000..dd5bbf9a4d7d717b74549a721e0f27083ed511ae Binary files /dev/null and b/mlp_maths/q6.PNG differ diff --git a/mlp_maths/q7.PNG b/mlp_maths/q7.PNG new file mode 100644 index 0000000000000000000000000000000000000000..a8acadbf960736c34cd382a1dfd693a04747549e Binary files /dev/null and b/mlp_maths/q7.PNG differ diff --git a/mlp_maths/q8.PNG b/mlp_maths/q8.PNG new file mode 100644 index 0000000000000000000000000000000000000000..ab5080828e9ee234a3581c97dada35d57be1f8e9 Binary files /dev/null and b/mlp_maths/q8.PNG differ diff --git a/mlp_maths/q9.PNG b/mlp_maths/q9.PNG new file mode 100644 index 0000000000000000000000000000000000000000..79574eaa274d409764a92244a7cccbc88699da88 Binary files /dev/null and b/mlp_maths/q9.PNG differ