Machine Learning & Deep Learning Flashcards
Define artificial intelligence.
Artificial intelligence allows computers to mimic the thinking capacity of humans.
What is meant by machine learning?
Machine learning is a type of artificial intelligence that enables computers to learn on its on its own. A computer or any other device equipped with machine learning can process data and evolve with minimal human assistance.
What is deep learning?
Deep learning can be considered as a machine learning technique that enables computers to adapt the way the human brain works completely.
List how deep learning differs from machine learning.
Deep Learning:
* Better capability
* Large amount of data is required as input
* The structure of the model is multi-layered
* Can function with almost no human assistance
* Algorithm can completely think on its own
Machine Learning:
* Accuracy and capability is comparatively less
* Amount of data required can be any amount
* The structure of simple
* Some human intervention is required from time to time
* A basic algorithm has to be generated by humans which automatically gets better
An Artificial Neural Network consists of multiple ________________ of interconnected artificial neurons.
Layers
Unsupervised machine learning can be used to detect _____________________ bank transactions.
Fraudulent
_______________________________ learning works by learning from labelled examples.
Supervised machine
The ___________________________ layers of ANN enable deep learning systems to uncover patterns and generate algorithms on their own.
Multiple hidden
Computers using reinforcement learning continuously interact with their _____________________.
Environment
The main objective of ________________________ is to train computer systems to mimic the way of thinking and judgement of human beings.
Machine Learning
Artificial intelligence is applicable in emails, social networking and video streaming platforms, online shopping websites, self driving vehicles and facial recognition software.
True
A device using reinforcement learning model aims to maximise the number of the negative signal it receives.
False
An ANN contains two types of layer: input and output
False
Unsupervised machine learning can be used for the detection of fraudulent transactions.
True
Computers use supervised machine learning to classify, sort or organize unlabelled data.
False