As indicated in lecture neural networks are ubiquitously used in classification and regression tasks every day across multiple domains. In this question you will use the online interactive tool provided by TensorFlow (an open-source machine learning framework often used for its deep learning capabilities) at the following website and answer the questions below: playground.tensorflow.org Create a neural network with 1 hidden layer with two neurons, one output node and input features X1 and X2 2 . Select the ratio of training to test data to be 70%, Noise=0, Batch size=10, learning rate=0.1, activation=tanh, regularization=None, Regularization Rate=0, Problem Type=Regression. Use the Multi-Gaussian data set.

(a) (5 points) Run the neural network until it seems to have converged (100-150 epochs). Examine the output plot and explain whether you believe the learned model is sufficient for the task (HINT: look at the images within each neuron). Provide a screen shot of the learned model and output.

(b) (8 points) Experiment with the number of neurons in the hidden layer, making observations with maximum of 500 epochs. Explain why you believe the output is as you observe. Provide 3-4 screen shots to show your observations.

(c) (12 points) Use the tool to experiment with including other input features and network hidden layers to find the network with fewest total hidden nodes that can achieve a training error of 0.003 or lower within 1000 epochs. Provide a screen shot of the learned model and output and explain how the network solves the problem by examining the images at each hidden neuron.

Please answer all! Thank you!