PRACTICE QUIZ

Cognitive systems learn, adapt, and keep getting smarter by learning from their interactions with us and from their own successes and failures, just like humans do.

Machine Learning uses computer algorithms to analyze data and make intelligent decisions by defining behavioral rules based on what it has learned, without being explicitly programmed. These algorithms continue to learn on the job.

This statement is not an attribute of either Machine Learning or Unsupervised Learning. Machine Learning techniques such as unsupervised learning are not fed rules. Rather they determine the rules from data.

Supervised learning relies on giving the algorithm human-labeled data for training. The greater the number of samples that the algorithm is trained on, the greater is its precision in classifying new data.

Training data is used to train the algorithm. It is the Validation data that is used to fine-tune algorithm’s parameters and evaluate how good the model is.

Deep Learning algorithms rely on several layers of processing units, or neurons, where each layer passes on its output to the next layer, which processes it and passes it onto the next. The number of layers and the types of functions that connect the outputs of each layer to the inputs of the next are configured by developers.

Computer Vision enables machines to interpret digital images and video sequences and perform tasks like object identification.

The process of generating natural voice starts with a neural network ingesting samples of a person’s voice until it can tell whether a new voice sample belongs to the same person. Then, a second neural network generates audio data and runs it through the first network to see if it validates it as belonging to the subject, which it does till such time that it generates an accurate voice sample.

AI learns in three different ways - Supervised, Unsupervised, and Reinforcement Learning.

Cognitive systems use processes similar to the decision-making process of humans to interpret and generate hypotheses about the information they read.

Programming all rules and moves of a game is not a true application of AI, rather training the machine to learn from data and enabling it figure out the moves and strategies for winning is how Machine Learning works.

Data Science is an interdisciplinary field encompassing the entire data processing methodology. While it uses AI techniques to derive insight from data, it is NOT a subset of AI.

Machine learning uses computer algorithms to analyze large data sets to find common patterns and and define behavioral rules based on what it has learned. Explanation: Unlike traditional algorithms which give answers based on predetermined set of rules, machine learning algorithms analyze input data and desired results to define behavioral rules based on which desired results can be achieved. The model can be continuously trained with new data sets. Explanation: Machine learning analyzes input data and answers to determine the set of rules and create the learning algorithm.

Classification is the process of extracting features from data and classifying the results into one or more categories.

Neural networks are the reason deep learning algorithms can continuously learn on the job and improve the quality and accuracy of results as datasets increase in volume over time.

Perceptrons are single-layered neural networks consisting of input nodes connected directly to an output node. Input layers forward the input values to the next layer, by means of multiplying by a weight and summing the results. An activation function determines how a node responds to its inputs and is a critical component to the success of a neural network.

Natural language is one of the most complex data for machine learning to work with. Natural language is highly contextualized, moreover humans view and use language conceptually rather than literally. Other types of data, be it auditory or visual data, have some form of discernible patterns, making it easier to work with than natural language.

Natural Language Processing uses machine learning and deep learning algorithms to deconstruct sentences grammatically, relationally, and structurally, to understand a word)s semantic meaning and it)s context of use. NLP systems are also able to understand intent and emotion, by drawing inferences through a broad array of linguistic models and algorithms.

Self-driving vehicles fuse laser data, vision data, and radar data to create a three-dimensional view of their driving environment helping them make accurate decisions on the road.

Visual attention is a limitation of human vision that computer vision can help makeup for. Human vision cannot attend to everything in its visual field, all at the same time, like computer vision can.