Format for the first midterm
The first midterm exam will focus on concepts. The exam will consist of a series of short answer questions. Most of these questions will ask you to explain some concept we have encountered.
Concepts to review
Here is a list of concepts that may appear on the exam. In each case be prepared to give a short explanation of the concept.
- Perceptron
- Perceptron learning rule
- Perceptron activation function
- Hidden layer
- Backpropagation
- Momentum
- Loss function
- ReLU activation function
- Sigmoid activation function
- Softmax activation function
- Batch
- Epoch
- Validation set
- Test set
- Mean square error loss function
- Categorical cross entropy
- Sparse categorical cross entropy
- Regularization
- Channels in an image
- Filter
- Image map
- Convolution layer
- Pooling
- Residual connection
- Keras dataset object