Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.


Machine Learning

Quantum algorithms for supervised and unsupervised machine learning

Zeyu Wang

on 30 September 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Machine Learning

You create these algorithms but then they do their own things.
Computers can unconsciously evolve programs to do things that no human could consciously program......
Supervised Learning
In machine learning, information processors perform tasks of sorting,assembling,assimilating and classifying information.
Supervised Learning
Even though we programmed these algorithms,what actually happens when it unfolds live,we don't control any more.
Arthur Samuel (1959) :
Machine Learning: Field of study that gives computers the ability to

learn without being explicitly programmed.
Supervised Learning
Unsupervised Learning
Quantum algorithms
Machine Learning
Machine Learning and Quantum Algorithms
Tom Mitchell (1998) :
Well-posed Learning Problem: A computer program is said to

learn from experience E
with respect to some task T and
some performance measure P
, if its performance on T, as measured by P, improves with experience E.
Thank you!
Quantum Machine Learning
Take time logarithmic in the number of vectors, an exponential speed-up over classical algorithms ( polynomial time ).
Quantum machine learning allows enhanced privacy

Supervised Learning
Unsupervised Learning
Machine Learning
Quantum Computing & Quantum computer
Quantum machine learning is about manipulating and classifying large amounts of data that is presented in arrays(rectors) and arrays of arrays(tensor products)
Quantum computers are good at manipulating vectors and tensor products in high-dimensional spaces.
The paper provides supervised and unsupervised quantum machine learning algorithms for cluster assignment and cluster finding.
Take time logarithmic in the number of dimensions, an exponential speed-up over classical algorithms ( polynomial time).
Estimating metrics between vectors in N-dimensional vector spaces
takes time:
Assigning N-dimensional vectors to one of several clusters of M states
takes time:
Only O(log(MN)) quantum data-base states are required to perform cluster assignment, while O(MN) are required to uncover the actual data.

The data-base user can still obtain information about the desired patterns, while the data-base owner is assured that the user has only accessed an exponentially small fraction of the data base.
Full transcript