Exam 6: Deep Learning and Cognitive Computing

What concept do CNN's use to avoid large numbers of weight parameters being defined and trained?

Which type of learning system is represented by the following process: input - simple features - more advanced features - mapping from features - output?

What is Keras, and how is it different from the other frameworks?

ANN are capable of solving complex problems and provide detailed explanations of their capabilities.

Typically, a neuron has more than ________ input.

Structured, human-mediated machine-learning approaches have been working fine for rather abstract and formal tasks.

Which type of a and a transfer function is described: operation increases in a line based on condition using an operation such as a=n.

Convolution layers are often followed by a pooling layer.

In the opening vignette, the results did not include:

What are the key attributes of cognitive computing systems?

In artificial neurons weight terms are adjustable but biased terms are fixed.

Which deep learning framework is particularly known to be an efficient framework for image processing due to incredible speed in processing image files?

CNNs are only applicable to image data sets.

Which type of learning system is represented by the following process: input - manually created representation - output?

What are the five steps in the backpropagation learning algorithm?

In the opening vignette, banks had begun to use deep learning to provide more accurate recognition of fraud.

Deep MLP and convolutional networks are specialized for processing a sequential grid of values.

Describe an MLP deep network. Why are these labeled as feedforward networks?

Deep neural networks are referred to as "deep" because they are primarily used to evaluate significant philosophical issues.

Who published a weekly supervised training image recognition deep learning project in May 2018?