Deep learning has been widely adopted in data science. A deep learning model learns to perform classification tasks directly from images, text or sound. The model is trained using a large set of labeled data and neural network architectures that contain many layers.

Keras is one of the most powerful and easy-to-use open-source libraries for developing and evaluating deep learning models. It is a high-level neural network API, capable of running on top of low-level library such as TensorFlow, Theano and CNTK. It enables fast experimentation through a high level, user-friendly, modular and extensible API. Keras code is portable and can be run on both CPU and GPU.

This workshop will provide hands-on exposure to implement deep learning models using Keras.

2 favorite thumb_down thumb_up 0 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist

Outline/Structure of the Workshop

  • An Overview of Keras Architecture
  • Basic Steps with Keras
  • Implementing Convolutional Neural Network
  • Implementing Recurrent Neural Network
  • Keras Tutorials and Examples
  • Conclusion and Future Scope

Learning Outcome

After attending this workshop, attendees will be able to…

  • Understand basics of Keras libraries.
  • Create deep learning models using sequential as well as functional APIs of Keras.
  • Develop deep learning based applications using Keras.

Target Audience

Students, faculty members, researchers and Industrialists whose areas of interest include deep learning.

Prerequisites for Attendees

  • Basic knowledge of Machine Learning
  • No experience with Keras or Python is required
schedule Submitted 1 month ago

Public Feedback

comment Suggest improvements to the Speaker

  • 45 Mins

    Artificial Intelligence (AI) has been rapidly adopted in various spheres of medicine such as microbiological analysis, discovery of drug, disease diagnosis, Genomics, medical imaging and bioinformatics for translating biomedical data into improved human healthcare. Automation in healthcare using machine learning/deep learning assists physicians to make faster, cheaper and more accurate diagnoses.

    We have completed three healthcare projects using deep learning and are currently working on three more healthcare projects. In this session, we shall demonstrate two deep learning based healthcare applications developed using TensorFlow. The discussion of each application will include the following: problem statement, proposed solution, data collected, experimental analysis and challenges faced to achieve this success. Finally, we will briefly discuss the other applications on which we are currently working and the future scope of research in this area.

  • 90 Mins

    Machine learning and deep learning have been rapidly adopted in providing solutions to various problems in medicine. If you wish to build scalable machine learning/deep learning-powered healthcare solutions, you need to understand how to use tools to build them.

    The TensorFlow is an open source machine learning framework. It enables the use of data flow graphs for numerical computations, with automatic parallelization across several CPUs, GPUs or TPUs. Its architecture makes it ideal for implementing machine learning/deep learning algorithms.

    This tutorial will provide hands-on exposure to implement Deep Learning based healthcare solutions using TensorFlow.