* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download A neuron receives input from other neurons
Functional magnetic resonance imaging wikipedia , lookup
Biochemistry of Alzheimer's disease wikipedia , lookup
Endocannabinoid system wikipedia , lookup
Human brain wikipedia , lookup
Selfish brain theory wikipedia , lookup
Human multitasking wikipedia , lookup
Brain morphometry wikipedia , lookup
Binding problem wikipedia , lookup
Multielectrode array wikipedia , lookup
Caridoid escape reaction wikipedia , lookup
Aging brain wikipedia , lookup
Haemodynamic response wikipedia , lookup
Neurolinguistics wikipedia , lookup
Artificial neural network wikipedia , lookup
Neuroinformatics wikipedia , lookup
Embodied cognitive science wikipedia , lookup
Neuroeconomics wikipedia , lookup
Neuroplasticity wikipedia , lookup
Neurophilosophy wikipedia , lookup
Neural oscillation wikipedia , lookup
Donald O. Hebb wikipedia , lookup
Premovement neuronal activity wikipedia , lookup
Mirror neuron wikipedia , lookup
History of neuroimaging wikipedia , lookup
Neurotransmitter wikipedia , lookup
Neuropsychology wikipedia , lookup
Central pattern generator wikipedia , lookup
Cognitive neuroscience wikipedia , lookup
Synaptogenesis wikipedia , lookup
Neural modeling fields wikipedia , lookup
Convolutional neural network wikipedia , lookup
Nonsynaptic plasticity wikipedia , lookup
Activity-dependent plasticity wikipedia , lookup
Neural engineering wikipedia , lookup
Neural correlates of consciousness wikipedia , lookup
Neural coding wikipedia , lookup
Clinical neurochemistry wikipedia , lookup
Molecular neuroscience wikipedia , lookup
Brain Rules wikipedia , lookup
Pre-Bötzinger complex wikipedia , lookup
Chemical synapse wikipedia , lookup
Stimulus (physiology) wikipedia , lookup
Mind uploading wikipedia , lookup
Optogenetics wikipedia , lookup
Feature detection (nervous system) wikipedia , lookup
Circumventricular organs wikipedia , lookup
Recurrent neural network wikipedia , lookup
Artificial general intelligence wikipedia , lookup
Single-unit recording wikipedia , lookup
Development of the nervous system wikipedia , lookup
Types of artificial neural networks wikipedia , lookup
Biological neuron model wikipedia , lookup
Holonomic brain theory wikipedia , lookup
Channelrhodopsin wikipedia , lookup
Neuroanatomy wikipedia , lookup
Synaptic gating wikipedia , lookup
Neuropsychopharmacology wikipedia , lookup
N. Laskaris Motivation ‘‘ Πρέπει να αναπτύξουµε, όσο πιο γρήγορα είναι δυνατό, την τεχνολογία προς στην κατεύθυνση εκείνη που θα επιτρέψει την άµεση επικοινωνία µεταξύ του ανθρώπινου εγκεφάλου και των υπολογιστών. Οι νοήµονες µηχανές θα πρέπει να συµβάλουν στην ανθρώπινη ευφυϊα και να µην την ανταγωνίζονται’’ --- Stephen Hawking Grand Vision Philosophical Inquiries What tasks are machines good at doing that humans are not? What tasks are humans good at doing that machines are not? What tasks are both good at? What does it mean to learn? How is learning related to intelligence? What does it mean to be intelligent? Do you believe a machine will ever be built that exhibits intelligence? Have the above definitions changed over time? If a computer were intelligent, how would you know? What does it mean to be conscious? Can one be intelligent and not conscious or vice versa? Although it may appear to be no more than a mass of tissue weighing a mere three pounds (1.350 Kgr), the brain is a remarkable organ It is critical to our survivial. Æ Without the brain, vital functions such as heart rhythms, breathing, and digestion would be impossible. But the brain does so much more !!! Did you enjoy your last meal? Do you remember the last movie you saw? Did it make you feel happy or sad? Can you trace all the steps you take to get from your house to the nearest convenience store? The brain is what enables us to have sensations, make decisions, and take action. It allows us to learn a whole lifetime of experiences, and gives us the ability for language and abstract thought. In short, the brain makes possible the human condition. How does it do it ? NeuroSience Functional Organization The brain contains over 100 billion specialized cells called neurons. Neurons can be thought of as the basic processing units of the brain and convey signals by passing electrical impulses called action potentials from one end of themselves to another. Action potentials are generated by the opening and closing of microscopic gates in the cell membrane. At the end of the axon, information is transferred to the next neuron via a specialized structure, called the synapse. The synapse is where individual neurons transmit information to other neurons. Neurons come very close to each other at the synapse, but do not actually touch. Communication between neurons happens when chemical signals are transmitted across a gap known as the synaptic cleft. The Brain as an Information Processing System The human brain contains about 10 billion nerve cells, or neurons. neurons On average, each neuron is connected to other neurons through about 10 000 synapses. (The actual figures vary greatly, depending on the local neuroanatomy.) The brain's network of neurons forms a massively parallel information processing system. This contrasts with conventional computers, in which a single processor executes a single series of instructions. On the contrary: neurons typically operate at a maximum rate of about 100 Hz, while a conventional CPU carries out several hundred million machine level operations per second. Despite of being built with very slow hardware, the brain has quite remarkable capabilities: its performance tends to degrade gracefully under partial damage. it can learn (reorganize itself) from experience. this means that partial recovery from damage is possible if healthy units can learn to take over the functions previously carried out by the damaged areas. it performs massively parallel computations extremely efficiently. For example, complex visual perception occurs within less than 100 ms, that is, 10 processing steps! it supports our intelligence and self-awareness. (Nobody knows yet how this occurs.) Neural Networks in the Brain The brain is not homogeneous. At the largest anatomical scale, we distinguish cortex, midbrain, brainstem, and cerebellum. Each of these can be hierarchically subdivided into many regions, and areas within each region, either according to the anatomical structure of the neural networks within it, or according to the function performed by them. The overall pattern of projections (bundles of neural connections) between areas is extremely complex, and only partially known. The best mapped (and largest) system in the human brain is the visual system, where the first 10 or 11 processing stages have been identified. We distinguish feedforward projections that go from earlier processing stages (near the sensory input) to later ones (near the motor output), from feedback connections that go in the opposite direction. In addition to these long-range connections, neurons also link up with many thousands of their neighbours. In this way they form very dense, complex local networks: Neurons & Synapses The basic computational unit in the nervous system is the nerve cell, or neuron. A neuron has: - Dendrites (inputs) - Cell body - Axon (output) -A neuron receives input from other neurons (typically many thousands). Æ Inputs sum (approximately). -> Once input exceeds a critical level, the neuron discharges a spike an electrical pulse that travels from the body, down the axon, to the next neuron(s). This spiking event is also called depolarization, and is followed by a refractory period, during which the neuron is unable to fire. The axon endings (Output Zone) almost touch the dendrites or cell body of the next neuron. Transmission of an electrical signal from one neuron to the next is effected by neurotransmittors, chemicals which are released from the first neuron and which bind to receptors in the second. This link is called a synapse. The extent to which the signal from one neuron is passed on to the next depends on many factors, e.g. the amount of neurotransmittor available, the number and arrangement of receptors, amount of neurotransmittor reabsorbed, etc. Variety of neurons: From Structure to Function The following properties of nervous systems will be of particular interest in our neurally-inspired models: parallel, distributed information processing high degree of connectivity among basic units connections are modifiable based on experience learning is a constant process, and usually unsupervised learning is based only on local information performance degrades gracefully if some units are removed etc.......... Artificial Neuron Models Computational neurobiologists have constructed very elaborate computer models of neurons in order to run detailed simulations of particular circuits in the brain. As Computer Scientists, we are more interested in the general properties of neural networks, independent of how they are actually "implemented" in the brain. This means that we can use much simpler, abstract "neurons", which (hopefully) capture the essence of neural computation even if they leave out much of the details of how biological neurons work. People have implemented model neurons in hardware as electronic circuits, often integrated on VLSI chips. A Simple Artificial Neuron Our basic computational element (model neuron) is often called a node or unit. It receives input from some other units, or perhaps from an external source. Each input has an associated weight w, which can be modified so as to model synaptic learning. The unit computes some function f of the weighted sum of its inputs Its output, in turn, can serve as input to other units. Fitting a Model to Data Actual automobile data : Miles per Gallon (MPG) vs Weight 74-cars Capturing the general trend: ‘‘the heavier the car the greater the consumption’’ Question : How can We ‘‘learn’’ something from this data’’ ? By using linear regression, we can draw the best-fit line y = w1*x + w0 This is a simple model that can be used in future for prediction purposes …… By comparing the best-fit linear model With the function implemented by the following neural net y = -0.6*x + 0.1 y2 = w21 y1 + w20 1.0 We realize that this naïve artificial neural net can, in principle, ‘‘learn’’ the same automobile data ….. - By taking advantage of nonlinearities in neural activations, we can improve the modeling task - By taking advantage of the multivariate nature of artificial NNets, we can enhance the information used in the modeling task 1. mpg: continuous 2. cylinders: multi-valued discrete 3. displacement: continuous 4. horsepower: continuous 5. weight: continuous 6. acceleration: continuous 7. model year: multi-valued discrete 8. origin: multi-valued discrete 9. car name: string (unique for each instance) Prediction using many variates Multivariate prediction - Learning concept - Storage of Knowledge Acquired