Download
1 / 31
320 likes | 456 Views
AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS. Master Thesis. Michal Trna michal.trna@gmail.com. = Overview =. Introduction to RNN Demo of the tool Application on the chosen domain.
E N D
AN INTERACTIVE TOOL FOR THE STOCK MARKET RESEARCH USING RECURSIVE NEURAL NETWORKS Master Thesis Michal Trna michal.trna@gmail.com
= Overview = • 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 = • 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 = 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 = 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 = Introduction to NN & RNN = • Mathematical model of neuron
= Introduction to NN & RNN = • 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 = • Artificial neural network • Properties • Adaptability • Fault tolerance • Knowledge representation, context • Non-linearity • I/O mapping
= Introduction to NN & RNN = • Hebbian theory • For p patterns of length n:
= Introduction to NN & RNN = • Feed-forward neural networks • Recursive neural networks
Bias Neuron j Summing junction Output Σ f xj Inputs . . . Activation function Synaptic weights = Introduction to NN & RNN = • Perceptron
= Introduction to NN & RNN = • Perceptron • Separability, linear classifier • XOR problem ↑ Linear separation of logical AND, logical OR and logical XOR
= Introduction to NN & RNN = • Multilayer perceptron
= Introduction to NN & RNN = • 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 = Introduction to NN & RNN = • Single-layer and Multi-layer perceptron
= Introduction to NN & RNN = • Recurrent networks (RNN) • Simple RNN: Elman/Jordan network • Fully connected: Hopfield network
Context layer = Introduction to NN & RNN = • Elman network
Context layer = Introduction to NN & RNN = • Jordan network
= Introduction to NN & RNN = • Hopfield Networks • Dynamic equation
= Introduction to NN & RNN = • Synaptic potential, threshold • Mode of operation • Synchronous • Asynchronous • Deterministic • Non-deterministic • Energy • Autoassociative memory • Capacity: 0.15 N
= Graph Approach = • Graph approach • Acquiring pattern ξ: • Hopfield network:
Red component Blue component = Graph Approach = • Coloring
= Graph Approach = • 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 = Graph Approach = • Tetrahedral property • Four possible configurations
= Graph Approach = • Parameters
= Graph Approach = • Energy point, projection to 2D • Energy lines • classes • Scalar energy • Control of the convergence
= Graph Approach = • Relative weight of neuron • contribution of this neuron to the component I or O • Deviation • “a hash function”
= Graph Approach = • Thresholds
= Tool = • 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
