Loading in 5 sec....

AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKSPowerPoint Presentation

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

- 67 Views
- Uploaded on

Download Presentation
## PowerPoint Slideshow about ' AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS' - ardara

**An Image/Link below is provided (as is) to download presentation**

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 - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript

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

Master Thesis

Michal Trna

= Overview = RECURSIVE NEURAL NETWORKS

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

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

= Introduction to NN & RNN = 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 RECURSIVE NEURAL NETWORKS

Nucleus

Axon

Dendrites

= Introduction to NN & RNN =- Non-local connection
- Plasticity, synaptic learning
- Creation and atrophy of the connections

Action potential

1-100m/s

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

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 RECURSIVE NEURAL NETWORKS

Neuron j

Summing junction

Output

Σ

f

xj

Inputs

.

.

.

Activation function

Synaptic weights

Recipients of the output

= Introduction to NN & RNN =- Mathematical model of neuron

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

- 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.

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

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

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

- Feed-forward neural networks
- Recursive neural networks

Bias RECURSIVE NEURAL NETWORKS

Neuron j

Summing junction

Output

Σ

f

xj

Inputs

.

.

.

Activation function

Synaptic weights

= Introduction to NN & RNN =- Perceptron

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

- Perceptron
- Separability, linear classifier
- XOR problem

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

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

- Multilayer perceptron

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

- 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 RECURSIVE NEURAL NETWORKS

Three layers

Two layers

Arbitrary set

XOR-like set

= Introduction to NN & RNN =- Single-layer and Multi-layer perceptron

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

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

= Introduction to NN & RNN = RECURSIVE NEURAL NETWORKS

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

- Energy
- Autoassociative memory
- Capacity: 0.15 N

= Graph Approach = RECURSIVE NEURAL NETWORKS

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

= Graph Approach = RECURSIVE NEURAL NETWORKS

- Tetrahedral property

1 RECURSIVE NEURAL NETWORKS

0

0

–1

0

1

1

–1

1

0

0

–1

1

0

1

–1

1

1

1

1

0

–1

–1

–1

= Graph Approach =- Tetrahedral property
- Four possible configurations

= Graph Approach = RECURSIVE NEURAL NETWORKS

- Parameters

= Graph Approach = RECURSIVE NEURAL NETWORKS

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

- Scalar energy
- Control of the convergence

= Graph Approach = RECURSIVE NEURAL NETWORKS

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

- Deviation
- “a hash function”

= Graph Approach = RECURSIVE NEURAL NETWORKS

- Thresholds

= Tool = RECURSIVE NEURAL NETWORKS

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

↑ Typical convergence path

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

Thank you for your attention! RECURSIVE NEURAL NETWORKS

Time for your questions

Download Presentation

Connecting to Server..