Convolutional neural networks (CNNs)

From Computer Science Wiki
Jump to: navigation, search

Exclamation.png This is student work which has not yet been approved as correct by the instructor

feed forward neural net diagram

Introduction

A convolutional neural networka group or system of interconnected people or things. is a class of feedforward (which means that the connections between the units do not form a cycle and every unit in a layer is connected with all the units in the previous layer, as shown in the picture) artificial neural networka group or system of interconnected people or things. that is used to analyzeBreak down in order to bring out the essential elements or structure. To identify parts and relationships, and to interpret information to reach conclusions. images. [1]

How does it work or a deeper look

One of the biggest advantages of CNNs over other image classification algorithms is that, like all Aritficial Neural Networksa group or system of interconnected people or things., they are relatively independent from pre-processing, or prior knowledge provided by humans. Instead of using hand-engineered algorithms, they learn on their own how to most accurately and effectively evaluateAssess the implications and limitations; make judgments about the ideas, works, solutions or methods in relation to selected criteria. their input through processing huge amounts of labelled information from large image databases. CNNs fundamentally work on the same set of rules as other feedforward neural networksa group or system of interconnected people or things.. They operate in two phases: the learning phase and the classification phase. [2]

In the learning phase, they take take input (in case of image processing - a set of numbers describing each pixel, e.g. numbers from 0-255 for greyscale) together with its correct classification (e.g. a given image description has to fit one category, e.g. “cat pictures” or “dog pictures”). The set of values describing a given image is presented at the inputs. It will then be transformed depending on the weights of each connection as it reaches the output layer. Each unit from the output layer belongs to a different category and so now the output of the networka group or system of interconnected people or things. is compared to the ideal output that would have been, has the pattern been correctly classified (the largest value in the correct category unit, very small values for other categories). On the basis of this comparison and through the use of advanced algorithms, such as backpropagation, all the connection weights are slightly modified to ensure that the next time the same information is presented at the inputs, the correct output unit has a higher value and the incorrect units have lower values than before. Ultimately the goal is that the networka group or system of interconnected people or things. can correctly classifyArrange or order by class or category. all the information-category pairs and learn to generalize and correctly classifyArrange or order by class or category. new, unknown inputs.

In the classification phase the connection weights are no longer changeable. The information given at the inputs will be transformed based on the fixed weights until it reaches the output layer. Now the classification is simple - the output unit with the highest value is selected as the best fitting category. Obviously, the classification phase is much faster and more simple than the learning phase. [3]

Examples

Ever since Alex Krizhevsky used CNNs to win the ImageNet competition in 2012 (basically, the annual Olympics of computer vision) dropping the classification error record from 26% to 15%, a host of companies have been using deep learning at the core of their services. Facebook uses neural nets for their automatic tagging algorithms, Google for their photo search, Amazon for their product recommendations, Pinterest for their home feed personalization, and Instagram for their search infrastructure. [4]


One of the new applications of CNNs at the frontier of new technologies is to use them in self driving cars to process and analyseBreak down in order to bring out the essential elements or structure. To identify parts and relationships, and to interpret information to reach conclusions. the environment around them.

Pictures, diagrams

Typical cnn.png

External links

  1. https://en.wikipedia.org/wiki/Convolutional_neural_network
  2. https://en.wikipedia.org/wiki/Feedforward_neural_network
  3. http://www.fon.hum.uva.nl/praat/manual/Feedforward_neural_networks_1__What_is_a_feedforward_ne.html
  4. https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/

References