2. Defination
• Convolutional neural networks are a specialized type of artificial neural networks that use a mathematical operation
called convolution in place of general matrix multiplication in at least one of their layers.They are specifically designed to
process pixel data and are used in image recognition and processing.
• Convolutional neural network is a class of deep learning methods which has become dominant in various computer vision
tasks and is attracting interest across a variety of domains.
• Convolutional neural network is composed of multiple building blocks, such as convolution layers, pooling layers, and fully
connected layers, and is designed to automatically and adaptively learn spatial hierarchies of features through a
backpropagation algorithm.
3. Architecture
• CNN is a mathematical construct that is typically composed of three types
of layers (or building blocks):
• Convolution layers (perform feature extraction) A convolution layer plays a
key role in CNN, which is composed of a stack of mathematical operations,
such as convolution, a specialized type of linear operation and where a
small array of numbers, called a kernel.
• pooling layers (perform feature extraction)
• Max Pooling
• Average Pooling
• fully connected layers. (maps the extracted features into final output, such
as classification)
4.
5. • CNN possesses many advantages
• Local connections
• Weight sharing
• Down-sampling dimensionality reduction
• APPLICATIONS
• Image recognition
• Video analysis
• Natural language processing
• Anomly Detection
• Drug Discovery
• Checkers Game
• Time Series Forecasting