Download Presentation

Loading in 3 Seconds

This presentation is the property of its rightful owner.

X

Sponsored Links

- 34 Views
- Uploaded on
- Presentation posted in: General

AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS

Master Thesis

Michal Trna

- Introduction to RNN
- Demo of the tool
- Application on the chosen domain

AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS

- Motivation of the NN

- Brain contains 50–100 billion neurons
- 1000 trillion synaptic connections
- Solvescomplex problems
- Recognition of complex forms
- Forms well-founded predictions

↑ Contours of the human brain

Drawing of neurons from the cerebellum of a pigeon by Ramón y Cajal (1911) →

Axon terminal

Nucleus

Axon

Dendrites

- Non-local connection
- Plasticity, synaptic learning
- Creation and atrophy of the connections

Action potential

1-100m/s

Hebb’s law:

- When an axon of cell A is near enough to excite cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.

Donald O. Hebb, 1949

i.e.:

- Cells that fire together, wire together.

- Hebbian learning / Synaptic learning
- Anti-Hebbian learning

Bias

Neuron j

Summing junction

Output

Σ

f

xj

Inputs

.

.

.

Activation function

Synaptic weights

Recipients of the output

- Mathematical model of neuron

- Artificial neural networks

- A neural network is a massively parallel distributed processor that has a natural propensity for storing experiential knowledge and making it available for use. It resembles the brain in two respects:
- 1.Knowledge is acquired by the network through a learning process.
- 2.Interneuron connection strengths known as synaptic weights are used to store the knowledge.

- Artificial neural network
- Properties
- Adaptability
- Fault tolerance
- Knowledge representation, context
- Non-linearity
- I/O mapping

- Hebbian theory

- For p patterns of length n:

- Feed-forward neural networks
- Recursive neural networks

Bias

Neuron j

Summing junction

Output

Σ

f

xj

Inputs

.

.

.

Activation function

Synaptic weights

- Perceptron

- Perceptron
- Separability, linear classifier
- XOR problem

↑ Linear separation of logical AND, logical OR and logical XOR

- Multilayer perceptron

- Multi-layer perceptron
- Learning algorithm = back-propagation
- generate the output
- propagates back to produce deltas of all output and hidden layers
- gradient of weights
- modify the weight in the (opposite) direction of grad.

Single layer

Three layers

Two layers

Arbitrary set

XOR-like set

- Single-layer and Multi-layer perceptron

- Recurrent networks (RNN)
- Simple RNN: Elman/Jordan network
- Fully connected: Hopfield network

Context layer

- Elman network

Context layer

- Jordan network

- Hopfield Networks

- Dynamic equation

- Synaptic potential, threshold
- Mode of operation
- Synchronous
- Asynchronous
- Deterministic
- Non-deterministic

- Energy
- Autoassociative memory
- Capacity: 0.15 N

- Graph approach
- Acquiring pattern ξ:
- Hopfield network:

Red component

Blue component

- Coloring

- Tetrahedral property

1

0

0

–1

0

1

1

–1

1

0

0

–1

1

0

1

–1

1

1

1

1

0

–1

–1

–1

- Tetrahedral property
- Four possible configurations

- Parameters

- Energy point, projection to 2D
- Energy lines
- classes

- Scalar energy
- Control of the convergence

- Relative weight of neuron
- contribution of this neuron to the component I or O

- Deviation
- “a hash function”

- Thresholds

- Time for a demo
- http://msc.michaltrna.info/markers/index.html

↑ Typical convergence path

- Outlooks, future lines
- To use deviation for discrimination of parasitic states
- Quantify the results
- Application on automatic trading

Thank you for your attention!

Time for your questions