1. Tune the parameters to get at least 95% accuracy.
2. Explain your process for selecting the activation functions, loss functions, and dense layer dimensionality of the output space.
3. Display the confusion matrix of your final model.

Create a model to optimize prediction of the IRIS dataset using a perceptron.

1. 1. Load the IRIS dataset and split the data into two with 70% for training and 30% for testing.

1. 2. Create a Perceptron class and instantiate a new Perceptron. Fit the data to the model for 10 training iterations. Compute the prediction.

e. Plot the prediction for 100 epochs.

Generate three clusters with 500 points each with a standard normal distribution but

σ₁ = (1.2,0.8)                µ₁ = (-2,-2)

with the following variance (σ) and means (µ):

σ₂ = (0.4, 1.3)

σ₃ = (0.8, 0.9)

µ₂ = (1,-1)

µ₃ = (6,12)