Convolutional Neural Networks and Computer Vision

Greetings, the title for our group project is Convolutional Neural Networks and Computer Vision with TensorFlow. Overall,  we're going to get specific and see how a special kind of neural network, convolutional neural networks (CNNs) can be used for computer vision (detecting patterns in visual data). In deep learning, many different kinds of model architectures can be used for different problems. For example, we could use a convolutional neural network for making predictions on image data and/or text data. However, in practice some architectures typically work better than others. Specifically, we're going to go through the following with TensorFlow:

• Getting a dataset to work with
• Architecture of a convolutional neural network
• A quick end-to-end example (what we're working towards)
• Steps in modelling for binary image classification with CNNs
  • Becoming one with the data
  • Preparing data for modelling
  • Creating a CNN model (starting with a baseline)
  • Fitting a model (getting it to find patterns in our data)
  • Evaluating a model
  • Improving a model
  • Making a prediction with a trained model
• Steps in modelling for multi-class image classification with CNNs 
  
  • Same as above (but this time with a different dataset)

About Us

Robotics Club USM, is a gathering/club that provide a platform for students who are interested to learn, research, and development about robot. In USM, Robotics Club is a club which is under the supervision of School of Electrical and Electronic Engineering. However, the club also consists of members from various schools for instance School of Mechanical Engineering, School of Chemical Engineering and etc. Basically this club is one of the clubs wholly organized by students where lecturers act as managers.

Recently, USM Robotics Club mainly focuses on Research and Development (R&D) to develop new technology to apply in the robotics for solving some specific tasks. By having R&D department, we manage to improve our technology level to get a better performance for our robots.

Hopefully with these skills and knowledge our members gain from here, they can develop a new and useful technology to have a better life for human-being in future.