Implement your own deep learning models from scratch with Tensorflow 2.0
This is the code repository for Hands-On Deep Learning with TensorFlow 2.0 [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
Are you eager to deep dive into the details of neural networks and would like to play with it? Do you want to learn Deep Learning Techniques to build projects with the latest Tensorflow 2.0. You may use Keras but it is a high-level implementation which itself uses Tensorflow in the backend and you can’t make changes up to that level in your model as of TensorflowKeras. A good data scientist must have the skill of how things are going on behind the scenes. This course will help you to be a good Data Scientist by giving hands-on knowledge of Tensorflow 2.0. You will implement real deep learning algorithms and will be available with all the implementation. Using implementation you will learn core details of a neural network like forward-propagation i.e, how to initialize weights and backpropagation i.e, how to update weights with gradient descent algorithm, Cost functions like cross entropy and much more. By the end of this course, you will be confident to implement your own neural network that is a very amazing thing you are adding to your toolbox.
- Understand what TensorFlow is, how TensorFlow works, from basics to advanced level with case-study based approach.
- Understand neural networks and how to implement them with TensorFlow via Churn Prediction Case Study.
- Implement a convolution neural network in TensorFlow for pneumonia detection from the x-ray case study.
- Implement a recurrent neural network for stock price prediction case study and improving accuracy with long short-term memory network.
- Learn about TensorBoard for monitoring, transformer, eager execution and debugging code with TensorFlow.
- Build Transfer learning in Tensorflow using TFlearn via object detection and opinion mining model.
Ekta Saraogi is a computer engineer by profession! She started her career as Java developer and delivered e2e SSO web portal for ARC, based out of Arlington, Virginia, USA. Her next venture was leading on java implementation and delivery for payment gateway solutions for AMEX UK. After an enriching stint in BFSI domain, she took the mantle of being a java architect for travel platform for Amadeus. Further to follow was leading e2e solution design for BT TV for UK’s flagship Telco British Telecom Plc; it is a key enabler to offer Quad-play to UK customers. During every role, she carried out and every stint she had, one thing that always intrigued her was the power of “data” to drive business outcomes; if driven by the right tools. Being hands-on with technology and driven by the quest to develop those “right tools”, she ventured into the field of Data Science to extract best out of her technical and business functional experience gained over 12 years, to drive and deliver cost-effective business analytics solution for global businesses. LinkedIn: https://www.linkedin.com/in/ektasaraogi
Akshat Gupta is experienced in Machine learning with more than 3+ years of experience working in the field. He’s currently working as a Machine Learning Engineer at Robofied. He has worked in various domains like Healthcare, Finance, Sales and Automation in Machine learning. He has done various machine learning projects with the Government of India (Ministry of microscale and medium enterprises), with companies and contributed to various open-source projects. He has a strong knowledge of Machine learning and Tensorflow. He’s also very active in research in Machine Learning, he’s has several publications currently going on and writes blogs on Machine Learning. LinkedIn: https://www.linkedin.com/in/akshat-rg/
This course is for developers who are familiar with Machine Learning concepts and want to get into Deep Learning using TensorFlow 2.0 in a compelling way. You must have basic knowledge of Python and of tensors. We will cover each and every core details of the Tensorflow 2.0 library in order to make you comfortable in working with it.
This course has the following requirements:
For an optimal experience with hands-on labs and other practical activities, we recommend the following configuration:
OS: Linux(Redhat or Debian based) or Windows (7 or 10)
Processor: i7(above 5th gen)
Jupyter Notebook, Latest Version
Python 3.5.x installed