Programming Assignment 5 - Build your own Conventional Neural Network After completing this project, you will be able to do the following:
Build neural network conveniently.
Configure with different regularization methods: Dropout, l1 or l2 regulation.
Dataset This dataset is provided by our current research project, which utilize 20 kHz acoustic sensing to sense ASL gestures. All the 10 ASL words perform by 5 subjects. All images are generated by using the short-time Fourier transform (STFT) to calculate a spectrogram as the feature representation of the reflected near-ultrasound waves. Based on the Doppler effect, sign language gestures, including both hands and arms, will cause phase and frequency changes of the reflected sonic wave. The spectrogram contains information in both frequency and time domains. The spectrogram is also defined as the Power Spectral Density of the function:
where x[n] is input signal, and ω[n−m] represents the overlapping Kaiser window function with an adjustable shape factor β that improves the resolution and reduces the spectral leakage close to the sidelobes of the signal. The coefficients of the Kaiser window are computed as:
This dataset has a training set of 5,000 examples, and a test set of 1,000 examples.