Intro to Neural Networks and Deep Learning
Deep learning (DL) is a subfield of Machine Learning that deals with algorithms inspired by the structure and function of the brain. DL has revolutionized the world with its advancement in technology, finding its application in every sector of business. Deep Learning models help advertisers leverage data to perform real-time bidding and targeted display advertising. It is also used to make weather predictions about rain, earthquakes, and tsunamis. With deep learning, machines can comprehend speech and provide the required output. It enables the machines to recognize people and objects in the images fed to it. TensorFlow is currently the most popular learning library in the world, based on the concept of tensors, which are vectors or matrices of n dimensions. This workshop will explore selected programming tools using python and/or Matlab and demonstrates the Deep Learning (DL) steps with examples. The focus will be handling of some of the widely used methods and key issues that students may come across, suggesting a number of discrete resolutions so as to provide optimal results on the accuracy and validity of Train and Test methodology.
Date and Time
Location
Hosts
Registration
- Date: 02 Jun 2023
- Time: 11:30 AM UTC to 12:30 AM UTC
-
Add Event to Calendar
Speakers
Dr. Muqri
Intro to Neural Networks and Deep Learning
Deep learning (DL) is a subfield of Machine Learning that deals with algorithms inspired by the structure and function of the brain. DL has revolutionized the world with its advancement in technology, finding its application in every sector of business. Deep Learning models help advertisers leverage data to perform real-time bidding and targeted display advertising. It is also used to make weather predictions about rain, earthquakes, and tsunamis. With deep learning, machines can comprehend speech and provide the required output. It enables the machines to recognize people and objects in the images fed to it. TensorFlow is currently the most popular learning library in the world, based on the concept of tensors, which are vectors or matrices of n dimensions. This workshop will explore selected programming tools using python and/or Matlab and demonstrates the Deep Learning (DL) steps with examples. The focus will be handling of some of the widely used methods and key issues that students may come across, suggesting a number of discrete resolutions so as to provide optimal results on the accuracy and validity of Train and Test methodology.
Biography:
Dr. Mohammad Muqri served as a professor at DeVry University for twenty years. He earned a MD from Spartan University, an MSEE in Computer Engineering from the University of Tennessee, Knoxville, an MBA from Keller School of Management, and a BSEE from NED University. His master’s thesis was in computer algorithms in communications and networking. He served as a postdoctoral research fellow for the University of Illinois, Chicago in Hypertension, Alzheimer studies, and high-performance computing for MRI and CT applications. He also worked as senior engineer (ASICs development) for Litton Guidance and Control Systems (Northrop Grumman). He has authored more than twenty papers related to software programming, biomedical engineering, signal processing, wireless communications, computer modeling, statistical process control and Monte Carlo simulations. He is an active member of ASEE, American Medical Association (AMA), IEEE Engineering in Medicine and Biology Society (EMBS) and peer reviewed more than 100 papers for ASEE and IEEE.
Address:United States
Agenda
- What is Deep learning and why do we need it ?
- Deep Learning Libraries
- Steps in Deep Learning Life Cycle
- Tensors and Neural Networks
- TensorFlow Computations and Data Flow Graph
- What are Keras and tf.keras
- Creating Simple Neural network in Keras
- MNIST Data Set Images
- How to train a CNN (Convolutional Neural Network )Model
- MNIST Handwritten Digit classification using Tensor Flow
- Fitting and Evaluating a CNN Model
- How to Visualize Deep Learning Models
- Plotting Model learning Curves
- Summary & Key Takeaways