Scribd
Upload
168 views11 pages

Artificial Intelligence and Machine Learning

This document discusses artificial intelligence and machine learning. It covers several subfields of AI studied in computer science, including planning, agents, search, constraints, knowledge representation, machine learning, uncertainty, natural language processing, robotics, and interfaces. It notes that most of the recent boom in AI is due to machine learning. Deep learning, Bayesian machine learning, and reinforcement learning are discussed as important types of machine learning. The document also briefly mentions exact reasoning in AI and some applications and supporting technologies.

Uploaded by

way2devraj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
168 views11 pages

Artificial Intelligence and Machine Learning

This document discusses artificial intelligence and machine learning. It covers several subfields of AI studied in computer science, including planning, agents, search, constraints, knowledge representation, machine learning, uncertainty, natural language processing, robotics, and interfaces. It notes that most of the recent boom in AI is due to machine learning. Deep learning, Bayesian machine learning, and reinforcement learning are discussed as important types of machine learning. The document also briefly mentions exact reasoning in AI and some applications and supporting technologies.

Uploaded by

way2devraj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

ARTIFICIAL INTELLIGENCE AND MACHINE

LEARNING

Arto Klami
Academy Research Fellow

University of Helsinki
Department of Computer Sciencec
Helsinki Institute for Information Technology HIIT
ARTIFICIAL INTELLIGENCE
AI is a subfield of computer science that studies intelligent systems

Subfields/topics in AI studied in CS (adapted from IJCAI):


• Planning and Scheduling
• Agent-based and Multi-agent systems
• Combinatorial & Heuristic Search
• Constraints & Satisfiability
• Knowledge Representation, Reasoning and Logic
• Machine Learning
• Uncertainty in AI
• Natural Language Processing
• Robotics and Vision
• AI interfaces (conversational, human-computer interaction)

Methods and algorithms vs applications


AI BOOM: THE ACADEMIC PERSPECTIVE
Participants in the leading ML/AI conference (NIPS)

3
AI BOOM: THE ACADEMIC PERSPECTIVE
Participants in the leading ML/AI conference (NIPS)

arXiv submissions doubling every year,


1800 AI-papers submitted in March 2017!

4
AI: MACHINE LEARNING
Most of the boom because of machine learning

Arthur Samuel (1957): “Field of study that gives computers the ability
to learn without being explicitly programmed.”

Tom Mitchell: “A computer program is said to learn from


experience E with respect to some class of tasks T and performance
measure P if its performance at tasks in T, as measured by P, improves
with experience E.”
• Learns from data or experience, by a quantifiable amount
• Solves particular task – or typically family of tasks
AI: MACHINE LEARNING
AI: MACHINE LEARNING
Deep learning:
“Deep learning allows computational models that are composed of multiple
processing layers to learn representations of data with multiple levels of
abstraction.”

Bayesian machine learning:


“How can a machine learn from experience? Probabilistic modelling provides
a framework for understanding what learning is and […] for designing
machines that learn from data acquired through experience.”

Reinforcement learning:
“Reinforcement learning is a branch of machine learning concerned with using
experience gained through interacting with the world and evaluative feedback
to improve a system's ability to make behavioural decisions.”
AI: MACHINE LEARNING
Deep learning:
“Deep learning allows computational models that are composed of multiple
processing layers to learn representations of data with multiple levels of
abstraction.”

Bayesian machine learning:


“How can a All threelearn
machine streams studied primarily
from experience? from
Probabilistic modelling provides
theunderstanding
a framework for perspectivewhat
of statistical
learning ismodeling
and […] for designing
machines that learn from data acquired through experience.”

Reinforcement learning:
“Reinforcement learning is a branch of machine learning concerned with using
experience gained through interacting with the world and evaluative feedback
to improve a system's ability to make behavioural decisions.”
AI: EXACT REASONING
Constrained reasoning: Decisions, search and optimization over
computationally hard (NP–complete and beyond) problems
• Combinatorial optimization, satisfiability, …
• Research in solving more complex problems efficiently
Note:$rough&estimates,&for&propositional&reasoning
1M War$Gaming
10301,020 5M
Case$complexity$

0.5M$ VLSI
10150,500 1M Verification

100K Military$Logistics
450K
106020
20K$
Chess$(20$steps$deep)
100K

No.$of$atoms 103010
10K$
on$the$earth Deep$space$mission$control
50K
Seconds$until$heat$ 1047
death$of$sun 100 Car$repair$diagnosis
1030 200$
Protein$folding
Calculation$
(petaflopByear)
100 10K 20K 100K 1M Variables
Picture  from  Kumar,  DARPA Rules$(Constraints)
AI: APPLICATIONS
Progress highlighted by human
interest applications, but the actual
research is in the core algorithms
• CS can solve some applications
internally – most progress in these
• For others, we need collaboration

Machine  translation
SUPPORTING TECHNOLOGIES
CS research also in useful tools that are not about AI as such
• Scalable computation, distributed computing, computation platforms
• Software systems, data science, IoT
• Theoretical computer science
• Security

How to recognize whether research is about AI?


• AI is goal-driven – does the proposal solve a problem or provide tools
for solving certain types of problems?
• Often involves learning from data, but not always

You might also like