# Big Data - Exam II

 neural computing a pattern-recognition methodology for machine learning with the ability to "learn" from data, and the ability to generalize artificial neural network (ANN) or neural network the resulting model from neural computing used for pattern recognition, forecasting, prediction, and classification weights provide the relative importance of each input in an artificial neural network Artificial Neural Network ANN neurons the main processing elements of a neural network node ANN equivalent of a soma input ANN equivalent of a dendrite output ANN equivalent of an axon weight ANN equibalent of a synapse soma/node middle of a neuron dendrites/input the portion of a network that receives signals axon/output the portion of a network responsible for sending signals to other cells synapse/weight the portion of a network that is able to alter signals by increasing or decreasing the strength of the connection transformation (transfer) function the function in an ANN that is responsible for the signal to "act" or "not" feedforward-backpropagation paradigm (packpropagation) allows all neurons to link the output in one layer to the input of the next layer, but does not allow any feedback linkage - the most commonly used network paradigm network organized neurons topologies network patterns of neurons artificial neurons the processing elements (PE) of an ANN which receives inputs, processes them, and delivers a single output hidden layer a layer of neurons that takes input from the previous layer and converts those inputs into outputs for further processing processing elements the "neuron" - performs the summation function parallel processing many processing elements perform their computations at the same time input represents a single element (ex: sales price) to be considered inputs several types of data, such as text, pictures, and voice, can be used as ____. output the solution to the problem - the purpose of the network computations - often in a 0 (no) or 1 (yes) format connection weights the key elements of an ANN - expfress the relative strength / mathematical value / importance of the input data or the many connections that transfer data from layer to layer weights through repeated adjustments of ____ a network learns weights store learned patterns of information summation function computes the weighted sums of all the input elements entering each processing element - multiplies each input value by its weight and totals the values for a weighted sum transformation (transfer) function combines (i.e., adds up) the inputs coming into a neuron from other neurons/sources and then produces an output sigmoid (logical activativation) function non-linear S-shaped transfer function in the range of 0 to 1 threshold value a hurdle value for the output of a neuron to trigger the next level of neurons supervised learning neural network learning where a sample training set is used to "teach" the network about its problem domain learning algorithm determines how the neural interconnection weights are corrected due to differences in the actual and desired output for a member of the training set supervised learning type of ANN learning used for prediction-type problems - an exemplary data set is used against a learning algorithm that adjusts as it examines its own outcomes against predetermined preferred outcomes - data is labeled (good or bad) unsupervised learning type of ANN learning used for clustering-type problems - learns patterns by repeatedly examining data that is not labeled learning rate a parameter that controls the rate of learning (too high or too low a rate causes issues) unserpervised learning network does not try to learn a target answer, instead, it learns a pattern through repeated exposures 1. collect organize & format the data 2. separate ate into training validation & testing sets 3. decide on a network architecture 4. select a learning algorithm 5. set network parameters & initialize their values 6. initialize weights & start training (& validation) 7. stop training, freeze the network weights 8. test the trained network 9. deploy the network for use on unknown new cases steps of the deployment process of an ANN sensitivity analysis the inputs are perturbed (changed) within allowable value ranges while the relative change on the output is measured/recorded sensitivity analysis developed to help users understand how the model performs - conducted on a trained ANN - results illustrate the relative importance of input variables logistical regression the regression type that can handle a categorical outcome variable Authormjweston ID237910 Card SetBig Data - Exam II DescriptionArtificial Neural Networks Updated2013-10-02T11:27:48Z Show Answers