01_intro Flashcards
Mapping Terminology, what is part of what?
AI (ML (Deep Learning)))
What is Artificial Intelligence?
Systems (S) that perceive their environment (E) and take actions (A) to maximize their chances of achieving their goals (P - Performance measure).
What is Machine Learning?
Machines learn from data without being programmed
“The Field of Study that gives computers the ability to learn without being explicitly programmed.”
What is Deep Learning?
End-to-end learning in deep neural networks.
What are Fields associated with AI/ML/DL?
Language defined: Mathematics, Statistics
Handling data: Data Science
Computational Prerequisites: Computer Science
Brain as Inspo: Neuroscience, Cognitive Science
What are 3 different approaches to Machine Learning?
1) Supervised Learning
2) Unsupervised Learning
3) Reinforcement Learning
What is supervised learning?
find a function (“task”)
that relates input data x
to output data y
by learning a specific task
such that f(x) = y
What is unsupervised learning?
find structure within a data set
find transformation T
that builds a compact internal representation
of unlabeled data x
to unveil its internal structure
What is reinforcement learning?
learn a task in a dynamic and responsive environment
What supervised tasks can be learned with image data?
Classification,
Object Detection and
Segmentation (Semantic image segmentation, pixel classification)
What supervised tasks can be learned with tabular data?
Classification,
Regression (Time-Series prediction),
Synthesis (Simulating new data)
What supervised tasks can be learned with textual data?
Classification,
Synthesis (Language Translation and Text Generation)
What supervised tasks can be learned with audio data?
Classification,
Synthesis (speech-to-text and text-to-speech)
What are supervised tasks?
Classification
Regression
Object Detection
Segmentation
Synthesis
What are unsupervised tasks?
Clustering
Dimensionality reduction
Reconstruction
Anomaly detection
