2. • What is machine learning?
• Examples
• Applications
• Training and testing
• Algorithms
• Conclusion
Agenda
3. • A branch of artificial intelligence, concerned with the design and development
of algorithms that allow computers to evolve behaviors based on empirical data.
• As intelligence requires knowledge, it is necessary for the computers to acquire
knowledge.
What is machine learning?
4.
5.
6.
7.
8.
9. NEURAL NETWORK
"...a computing system made up of a number of
simple, highly interconnected processing elements,
which process information by their dynamic state
response to external inputs.”
10. Applications
• Face detection
• Object detection and recognition
• Image segmentation
• Multimedia event detection
• Economical and commercial usage
11. With fully Self-Driving Technology,
you’ll be able to get where you want to go at
the push of a button—without the need for a
person at the wheel.
Face Recognition automatically
determines if two faces are likely to
correspond to the same person.
Speech Recognition is invading our
lives. It’s built into our phones, our game
consoles and our smart watches. It’s even
automating our homes.
12.
13.
14.
15.
16.
17.
18.
19.
20. Robotics and ML
Areas that robots are used:
Industrial robots
Military, government and space robots
Service robots for home, healthcare, laboratory
Why are robots used?
Dangerous tasks or in hazardous environments
Repetitive tasks
High precision tasks or those requiring high quality
Labor savings
Control technologies:
Autonomous (self-controlled), tele-operated (remote control)
22. ALVINN
Drives 70 mph on a public highway Predecessor of
the Google car
Camera
image
30x32 pixels
as inputs
30 outputs
for steering
30x32 weights
into one out of
four hidden
unit
4 hidden
units
24. DEEP LEARNING
It is the class of machine learning algorithm.
It is based on artificial neural network.
It has been used by Google's deep mind to play the
ancient Chinese game, 'Go’.
Machines have Over smarted Human Brains
25. Types of training
• Supervised learning: uses a series of labelled examples with direct
feedback
• Reinforcement learning: indirect feedback, after many examples
• Unsupervised/clustering learning: no feedback
• Semi supervised
28. • The success of machine learning system also depends on the algorithms.
• The algorithms control the search to find and build the knowledge structures.
• The learning algorithms should extract useful information from training examples.
Algorithms
29. ML in a Nutshell
• Tens of thousands of machine learning algorithms
• Hundreds new every year
• Every machine learning algorithm has three components:
• Representation
• Evaluation
• Optimization
30. Representation
• Decision trees
• Sets of rules / Logic programs
• Instances
• Graphical models (Bayes/Markov nets)
• Neural networks
• Support vector machines
• Model ensembles
• Etc.
31. Evaluation
• Accuracy
• Precision and recall
• Squared error
• Likelihood
• Posterior probability
• Cost / Utility
• Margin
• Entropy
• K-L divergence
• Etc.
33. Conclusion
We have a simple overview of some techniques and
algorithms in machine learning. Furthermore, there are more and
more techniques apply machine learning as a solution. In the future,
machine learning will play an important role in our daily life.