Support Vector Machines

Convolutional N eural Networks By Roger Ballard Tanqiuhao Chen A Brief Introduction to Neural Networks Neural networks are a supervised learn ing classification algorithm Given sufficient training data, a sufficie ntly large neural network can approxim ate any function from Rn to Rm Neural networks require a ton of training da

ta Image credit: https://commons.wikimedia.org/wiki/File:Colored_neural_network.svg Neural Network Topology A traditional neural network consists of multiple layers of fully-connected perce ptrons Data flows through the network from th e input layer, through the hidden layers, to the output layer Image credit: https://commons.wikimedia.org/wiki/File:Colored_neural_network.svg

Anatomy of a Perceptron A perceptron has n inputs, and 1 output Calculates a weighted sum of the inputs is the vector of all weights associated with each of the inputs is the bias value (which allows the function to have nonzero outp ut when the input is zero) Applies the chosen activation function to the weighted sum There are multiple possible functions, but the logistic function

and the leaky rectified linear function are two common choices Image credit: https://www.hiit.fi/u/ahonkela/dippa/node41.html https://commons.wikimedia.org/wiki/File:Logistic-curve.svg Training a Neural Network Method called backpropagation Based on gradient descent Calculate the result of running input through the network Compare to known/desired output Calculate the amount of error using a cost function Quadratic cost / sum squared error: chosen because the derivative is easy to co mpute, and it is a simple cost function Kullback-Leibler divergence: chosen because it measures the error in terms of i

nformation entropy Training a Neural Network (continued) Move backwards through the network, calcu lating the partial derivative of the cost with r espect to each of the parameters Also known as the cost function gradient Update each parameter proportionally to its partial derivative, using the training constan t Apply repeatedly with multiple inputs until t he cost function converges to a local minimu

m Image credit: http://charlesfranzen.com/posts/multiple-regression-in-python-gradient-descent/ What Makes a Convolutional Network D ifferent Images have certain properties that lead to the solution provided by CN Ns Images are big; a fully-connected network for an image would have an enormous n umber of parameters and be extremely difficult to train If the ability to recognize a feature is useful in one part of an image, it is likely to be useful everywhere in the image Convolution neural networks introduce two new types of layers, on top

of the traditional fully connected layers Convolutional layers Pooling layers Convolutional Layers The same perceptrons are applied to multiple different regions of t he input Mathematically, this is a convolution, which gives CNNs their name Hyperparameters:

Receptive field Depth Stride Zero-padding mage credit: https://commons.wikimedia.org/wiki/File:Conv_layers.png https://commons.wikimedia.org/wiki/File:Conv_layer.png Pooling Layers

Reduces the size of a layers output Useful to start recognizing higher-level features Traditionally max-pooling, but other methods are possible Parameters: Filter size Stride Zero-padding (If necessary) Image credit: https://commons.wikimedia.org/wiki/File:Max_pooling.png Traditional Convolutional Network Topo logy

Convolutional layers to extract features Pooling layers between convolutional layers, to increase scale and extract higher-level features at eac h layer End with several fully-connected layers to perform classification based off of the extracted features Image credit: http://www.computervisionblog.com/2015/04/deep-learning-vs-probabilistic.html

Recently Viewed Presentations

• Times New Roman Arial 宋体 WP Greek Century Symbol PMingLiU Default Design 1_Default Design 3_Default Design Microsoft Graph 97 Chart Microsoft Excel Worksheet Microsoft Imager Picture Microsoft Word Document Black Carbon:Global Budget and Impacts on Climate Slide 2 Scanning electron...
• Objectives of Presentation. Explain advances in neuroscience and impact on the field of rehabilitation. Discuss development and data on an efficacious speech treatment LSVT LOUD. Briefly describe development and key aspects of limb motor treatment LSVT BIG. Outline future directions...
• Homeostasis refers to maintaining internal stability within an organism and returning to a particular stable state after a fluctuation. ... Whether at the level of the milieu intérieur or the cytoplasm of a single cell, homeostasis occurs at a price:...
• Where: Ohio Valley Area, Canada region. ... John Adams, a well known Mass. lawyer, defended them. He believed that in a free country every person accused of a crime had a right to a lawyer and fair trail. ... See...
• Conclusions New physics domain in HEP simulation Wide interest in the user community A wealth of physics models A rigorous approach to software engineering Significant results from an extensive validation programme A variety of applications in diverse domains Homogeneous Phantom...
• unscramble these words. siuitbnisg. subitising. patt pahr rwole. part part whole. nunser seebm. number sense. mrazy rxieduspun mceb. crazy mixed up numbers. aunberktml
• Friction arises in part because of the roughness of the surfaces in contact, as seen in the expanded view. ... N is equal in magnitude to w⊥ , so there is no motion perpendicular to the slope. ... Which method...
• Manager Influence. Input for operation and limiting factor for growth rate, team dynamic. Managerial development as an inducement for growth, firm-specific experience for new managerial resources, economization through routine development and codification ... Japanese parent firm is listed in ...