Deep Learning Fundamentals for Computer Vision to be conducted by Prof Violeta Homes from UK. 

Upon successful completion of the workshop, and the online resources (within 30 days), participants will receive NVIDIA  Deep Learning Institute Certification to recognize subject matter competency and support professional career growth. 

SEATS ARE LIMITED: So if you are interested in attending this workshop, please email us on icabcd.org@gmail.com latest by Monday 15th July 2019. You will need to carry your own laptop for this session.

Workshop Brief:
Deep Learning is present in our day-to-day life. Siri, Alexa, and Google Assistant are reducing the barrier to entry to our online world from knowing how to spell and search to knowing how to speak. Netflix and Amazon allow us to filter through endless categories of offerings to find out what’s right for us. Combining Computer Vision with control systems opens the door to autonomous machines such as self-driving cars. And there are many more applications of deep learning

Deep learning (DL) brings a significant shift in the Machine learning (ML) paradigm. In contrast to traditional ML, the DL approach is to teach the computer the rules for performing the task directly from data. A data scientist usually provides a deep neural network with thousands of examples and train it how to perform the task. Consequently, less or rather no time is spend on feature engineering, but on dataset engineering. The advantages of DL approach include reduced reliance on domain-specific experts, the ability to extend and adapt to new data by retraining the network, and immense performance improvements using GPUs accelerators.

As a result, the deep learning approach can be more accurate, with significantly less human effort, but requires more data. The aim of this presentation/demonstration is to explore Deep Learning Fundamentals for Computer Vision. It is based on the Deep Learning Institute courses which are designed to be a hands-on experience with Deep Learning: https://www.nvidia.com/en-us/deep-learning-ai/education/. 

While all of the projects in the demonstration will be focused on computer vision, the concepts that are covered are broadly applicable across many deep learning applications. The workshop will start by introducing the concept of “training” and how it removes the constraints associated with traditional programming. The three ingredients that make deep learning powerful are:

·         Deep Neural Networks

·         The GPU

·         Big Data

We will demonstrate how to “deploy” solutions created with Deep Learning into real-world applications, highlighting the difference between training environments and deployment environments, and outline how to create applications that use the state-of-the-art in Deep Learning using existing models.

At the conclusion of the workshop, you will have an understanding of the fundamentals of deep learning and be able to:

● Implement common deep learning workflows, such as image classification and object detection.

● Experiment with data, training parameters, network structure, and other strategies to increase performance and capability of neural networks.

● Integrate and deploy neural networks in your own applications to start solving sophisticated real-world problems.

Delegates will be able to complete any outstanding work from the Fundamentals of Deep Learning for Computer Vision course using online resources (within 30 days).

Certification: Upon successful completion of the workshop, and the online resources (within 30 days), participants will receive NVIDIA DLI Certification to recognize subject matter competency and support professional career growth.