Page 314 - AI Computer 10

• Average Pooling: As its name implies, average pooling computes the average of the elements present in
the portion of the image covered by the kernel. Thus, average pooling produces the average of features
present in different sections of the feature map.
u Fully Connected Layer: The last layer in the Convolution Neural Network is the Fully Connected Layer.
The basic objective of fully connected layer is to classify the images on the basis of input. The result of
convolution/pooling process acts as an input for the fully connected layer. In a fully connected layer, the
output of convolution/pooling is flattened into a single vector of values, each representing a probability
that a certain feature belongs to a label.

Simply put, the fully connected layer is responsible to predict the best label for an image on the basis of the
result of convolution or pooling layer.

NO-CODE AI TOOLS FOR COMPUTER VISION

No-code AI tools for computer vision enables individuals and organisations to develop and implement image and
video analysis solutions without requiring extensive programming skills. These platforms employ user-friendly
interfaces, often featuring drag-and-drop functionality that empower users to build, train, and deploy computer
vision models efficiently.
Some of the popular no-code AI tools specifically designed for computer vision tasks are:
u Lobe.ai: Lobe.ai was a user-friendly, no-code machine learning platform developed by Microsoft that
allowed users to build and train custom machine learning models for image classification without requiring
much knowledge of programming. It worked with image classification and allowed a set of images with
labels and automatically found the most optimal model to classify the images. (Please notice that Lobe.ai is
not under development anymore)
u Teachable Machine: Teachable Machine is a web-based tool developed by Google that allows users to
create custom machine learning models easily and intuitively without any coding knowledge. It is designed
to be accessible to everyone, making machine learning technology more approachable and user-friendly.

180
180