Cuestionario: Introduction to AI and Machine Learning — 4 preguntas

1. How do Narrow AI and General AI differ from each other?

A. Narrow AI is focused on specific tasks, whereas General AI aims for broad, human-like cognitive abilities.

B. Narrow AI is a theoretical concept, and General AI is already widely used in everyday technology.

C. Narrow AI is designed for general intelligence, while General AI is task-specific.

D. Narrow AI can perform multiple tasks, but General AI is limited to one.

Answer: (A)

Explicación

According to the source, Narrow AI systems are designed to perform specific tasks, while General AI aims to develop machines with broad, human-like cognitive abilities. This makes option three the correct choice, as it accurately describes their fundamental difference.

2. In what order are the main topics introduced in the course regarding machine learning and AI concepts?

A. Deep Learning Techniques, Introduction to AI, Machine Learning Basics, Supervised Learning

B. Introduction to AI, Deep Learning Techniques, Machine Learning Basics, Supervised Learning

C. Introduction to AI, Machine Learning Basics, Supervised Learning, Deep Learning Techniques

D. Machine Learning Basics, Introduction to AI, Deep Learning Techniques, Supervised Learning

Answer: (C)

Explicación

The course outline shows that the topics are introduced in the following order: Introduction to AI, then Machine Learning Basics, followed by Supervised Learning, and finally Deep Learning Techniques. This sequence reflects the logical progression from general AI concepts to specific, advanced machine learning methods.

3. What is the primary role of supervised learning in machine learning systems?

A. To identify patterns in unlabeled data

B. To enable models to predict outcomes based on labeled data

C. To reduce the dimensionality of data features

D. To cluster data points into groups without labels

Answer: (B)

Explicación

Supervised learning's primary role is to enable models to predict outcomes based on labeled data, as explicitly stated in the source. It uses labeled data to train models that can predict specific results, unlike clustering or dimensionality reduction, which serve different purposes.

4. How should a practitioner apply backpropagation when training a neural network to improve its performance?

A. Initialize the network weights randomly and then use backpropagation to iteratively adjust them based on the error signals.

B. Apply backpropagation after training to check the accuracy of the model.

C. Use backpropagation to generate new data points to expand the training set.

D. Manually change the weights based on trial and error to see which configuration minimizes the error.

Answer: (A)

Explicación

Backpropagation is used during the training process to iteratively adjust the network's weights by propagating the error backward and updating weights to minimize this error, thus improving the model's performance.