Presentation is loading. Please wait.

Presentation is loading. Please wait.

Machine Learning. Learning agent Any other agent.

Similar presentations


Presentation on theme: "Machine Learning. Learning agent Any other agent."— Presentation transcript:

1 Machine Learning

2 Learning agent Any other agent

3 Learning agent learning element: responsible for making improvements performance element : responsible for selecting external actions critic : gives feedback to the learning element on how the agent is doing with respect to a fixed performance standard and determines how the performance element should be modified to do better in the future. problem generator : responsible for suggesting actions that will lead to new and informative experiences

4 Structural organization of levels in biological nervous systems.

5 Human brain

6 Artificial neurons Neurons work by processing information. The McCullogh-Pitts model Inputs Output w2w2 w1w1 w3w3 wnwn w n-1... x 1 x 2 x 3 … x n-1 x n y

7 Artificial neural network (ANN) is a mathematical model or computational model based on biological neural networks Artificial Neural Network consists of neurons arranged in layers Neurons act as parallel processor Neurons are connected with each other vi connection. there are weights associated with connections Implementation: Learning testing

8 Artificial neural networks Inputs Output An artificial neural network is composed of many artificial neurons that are linked together according to a specific network architecture. The objective of the neural network is to transform the inputs into meaningful outputs.

9 Artificial neural networks Dendrites: Input Layer Axon : Output Layer Soma: Net( weighted sum of input y_in) and activation function Synapse: Weights

10 Why use ANN? -Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience. -Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time. -Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability. -Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage.

11 ANN Characterization ANN can be characterized by: Activation function Weights Adjustment (learning algorithm) Architecture

12 Learning Algorithm Learning in ANN is Weights adjustment to get desired output To minimize the error To gain more experience Learning Supervised unsupervised

13 Supervised Learning There is supervisor during learning process Input and output are known The job of ANN is to classify any new input according to known classes Example : teaching baby the difference pens and other things LVQ (learning vector quantization)

14 Unsupervised learning Input known but output unknown The classes are unknown to ANN Job of ANN is to find similarities between input and divide them into categories (cluster) SOM (Self organizing map)

15 Architecture Feed forward allow signals to travel one way only; from input to output. There is no feedback (loops) Multi layer

16 Architecture Feedback networks signals travelling in both directions by introducing loops in the network

17 Decision Tree Representation Outlook Humidity Wind Sunny Overcast Rain High NormalStrong Weak Decision Tree for the concept PlayTennis

18 Pattern recognition system.

19 Flow chart of machine learning for pattern recognition.

20 Bayes classifier

21 Approaches

22 What is a Concept? A Concept is a a subset of objects or events defined over a larger set [Example: The concept of a bird is the subset of all objects (i.e., the set of all things or all animals) that belong to the category of bird.] Things Animals Birds Cars

23 What is Concept-Learning? Given a set of examples labeled as members or non-members of a concept, concept- learning consists of automatically inferring the general definition of this concept. In other words, concept-learning consists of approximating a boolean-valued function from training examples of its input and output.

24


Download ppt "Machine Learning. Learning agent Any other agent."

Similar presentations


Ads by Google