* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Introduction to Programming - Villanova Computer Science
Brain Rules wikipedia , lookup
Nonsynaptic plasticity wikipedia , lookup
Neuroeconomics wikipedia , lookup
Feature detection (nervous system) wikipedia , lookup
Neuroanatomy wikipedia , lookup
Perceptual learning wikipedia , lookup
Artificial neural network wikipedia , lookup
Development of the nervous system wikipedia , lookup
Activity-dependent plasticity wikipedia , lookup
Biological neuron model wikipedia , lookup
Single-unit recording wikipedia , lookup
Holonomic brain theory wikipedia , lookup
Donald O. Hebb wikipedia , lookup
Catastrophic interference wikipedia , lookup
Convolutional neural network wikipedia , lookup
Learning theory (education) wikipedia , lookup
Pattern recognition wikipedia , lookup
Eyeblink conditioning wikipedia , lookup
Neuropsychopharmacology wikipedia , lookup
Concept learning wikipedia , lookup
Neural modeling fields wikipedia , lookup
Nervous system network models wikipedia , lookup
Synaptic gating wikipedia , lookup
Recurrent neural network wikipedia , lookup
7: Introduction to Neural Networks CSC 4510 – Machine Learning Dr. Mary-Angela Papalaskari Department of Computing Sciences Villanova University Course website: www.csc.villanova.edu/~map/4510/ Some of the slides in this presentation are adapted from: • Prof. Frank Klassner’s ML class at Villanova • the University of Manchester ML course http://www.cs.manchester.ac.uk/ugt/COMP24111/ • The Stanford online ML course http://www.ml-class.org/ CSC 4510 - M.A. Papalaskari - Villanova University 1 Machine learning problems • Supervised Learning – Classification – Regression • Unsupervised learning Others: Reinforcement learning, recommender systems. Also talk about: Practical advice for applying learning algorithms. CSC 4510 - M.A. Papalaskari - Villanova University 2 Motivation – part 1 • Learning a non-linear function CSC 4510 - M.A. Papalaskari - Villanova University 3 What is this? You see this: But the camera sees this: Computer Vision: Car detection Not a car Cars Testing: What is this? pixel 1 Learning Algorithm pixel 2 Raw image pixel 2 Cars “Non”-Cars pixel 1 pixel 1 Learning Algorithm pixel 2 Raw image pixel 2 Cars “Non”-Cars pixel 1 pixel 1 Learning Algorithm pixel 2 Raw image pixel 2 Why not apply logistic regression? Cars “Non”-Cars pixel 1 Reminder: logistic regression can do non-linear Non-linear decision boundaries Add some higher-order terms? x2 1 1 -1 -1 x1 Predict “ “ if pixel 1 Learning Algorithm pixel 2 50 x 50 pixel images→ 2500 pixels (7500 if RGB) Raw image pixel 2 pixel 1 intensity pixel 2 intensity pixel 2500 intensity Cars “Non”-Cars pixel 1 Quadratic features ( ): ≈3 million features Motivation – part 2 • Take inspiration from the brain CSC 4510 - M.A. Papalaskari - Villanova University 11 Neural Networks Origins: Algorithms that try to mimic the brain. • Was very widely used in 80s and early 90s; • popularity diminished in late 90s. • Recent resurgence: State-of-the-art technique for many applications The “one learning algorithm” hypothesis Auditory Cortex Auditory cortex learns to see [Roe et al., 1992] The “one learning algorithm” hypothesis Somatosensory Cortex Somatosensory cortex learns to see [Metin & Frost, 1989] Sensor representations in the brain Seeing with your tongue Human echolocation (sonar) Haptic belt: Direction sense [BrainPort; Welsh & Blasch, 1997; Nagel et al., 2005; Constantine-Paton & Law, 2009] Implanting a 3rd eye Neuron in the brain Input signals sent from other neurons If enough sufficient signals accumulate, the neuron fires a signal. Connection strengths determine how the signals are accumulated Neurons in the brain [Credit: US National Institutes of Health, National Institute on Aging] Comparing Carbon & Silicon Human Brain Computational Units: O(1011) neurons Storage Units: O(1011) neurons, O(1014) synapses Cycle Time: O(10-3) sec, Bandwidth: O(1014) bits/sec Neuron Updates/sec: O(1014) Computer Computational Units: 1 CPU, 107 gates Storage Units: O(1011) bits RAM, O(1012) bits disk Cycle Time: O(10-8) sec, Bandwidth: O(108) bits/sec Neuron Updates/sec: O(108) The neuron model McCulloch & Pitts 1943 • Compute weighted sum of inputs and “fire” if above threshold value CSC 4510 - M.A. Papalaskari - Villanova University 19 • input signals ‘x’ and coefficients ‘w’ are multiplied • weights correspond to connection strengths • signals are added up – if they are enough, FIRE! x1 x2 x3 incoming signal add w1 w2 a M xw i 1 i i if (a t ) output 1 else output 0 w3 connection strength activation level output output signal signal Activation Functions A neuron can compute…. The perceptron Rosenblatt 1958: Training algorithm Neural Net • A single neuron • Adjustable synaptic weights CSC 4510 - M.A. Papalaskari - Villanova University 23 Perceptron learning 1. Initialize weights and thresholds to random numbers between -0.5 and 0.5 2. Activate perceptron 3. Update weights: wi(p+1) = wi(p) + α * xi(p) * err(p) 4. Iterate until Convergence Example: Perceptron learning logical AND 25 Representation Limits for perceptron Linear Separability