Employing Intel Deep Learning SDK Toward Bettering Image Recognition Models

In this case study, the challenge explored involves LeNet*, one of the prominent image recognition topologies for handwritten digit recognition.   In the case study, we dive into how the training tool can be used to visually set up, tune, and train the Mixed National Institute of Standards and Technology (MNIST) dataset on Caffe* optimized for Intel® architecture. Data scientists are the intended audience.

One of the main advantages of using the Intel Deep Learning SDK to train a model is its ease of use. As a data scientist, your focus would be more on easily preparing training data, using existing topologies where possible, designing new models if required, and train models with automated experiments and advanced visualizations. The training tool provides all of these benefits while also simplifying the installation of popular deep learning frameworks.

• The first positive impact of this case study involves enhancing one's understanding of how the human visual system and convolutional neural networks work.  In doing so, one receives great exposure into LeNet*.

• Getting insight into MNIST dataset is the second positive impact of this case study. To increase the variation in data, the final MNIST collection uses 30k images from each dataset for training and 5k images from each for testing.

• Using the Intel® Deep Learning SDK to train the model is the third positive impact of this case study.  One of the main advantages of using the Intel Deep Learning SDK to train a model is its ease of use. As a data scientist, your focus would be more on easily preparing training data, using existing topologies where possible, designing new models if required, and train models with automated experiments and advanced visualizations.