To develop and train a multi-layer perceptron (MLP) neural network model to accurately classify audio recordings into two categories: cat sounds and dog sounds.

This assignment requires you to multi-layer perceptron to classify animal sounds of two classes' only cats and dogs. Then, measure the accuracy of your neural network model.

• Ensure the dataset is balanced in terms of the number of samples for each class.
• The data should be pre-processed into a suitable format for neural network training (e.g., Mel-frequency cepstral coefficients (MFCCs), spectrograms)
• Design a multi-layer perceptron neural network using a framework of your choice (e.g., TensorFlow, PyTorch, Keras, or SKlearn).
• Split the dataset into training, validation, and test sets.
• Train the model on the training set. Implement batch learning and an appropriate loss function.
• Validate the model using the validation set to tune hyperparameters (like learning rate, number of hidden units, etc.)
• Evaluate the final model on the test set.
• Calculate the model's accuracy, and optionally other metrics like precision, recall, and F1-score.
• BONUS: Provide a confusion matrix to show the model's performance in classifying each class.

https://www.kaggle.com/datasets/mmoreaux/audio-cats-and-dogs