Neural Network from Scratch in TensorFlow
How to implement a neural network from scratch using TensorFlow.
How to solve a multi-class classification problem using the neural network implementation.
In this 2-hours long project-based course, you will learn how to implement a Neural Network model in TensorFlow using its core functionality (i.e. without the help of a high level API like Keras). You will also implement the gradient descent algorithm with the help of TensorFlow's automatic differentiation. While it’s easier to get started with TensorFlow with the Keras API, it’s still worth understanding how a slightly lower level implementation might work in tensorflow, and this project will give you a great starting point. In order to be successful in this project, you should be familiar with python programming, TensorFlow basics, conceptual understanding of Neural Networks and gradient descent. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.
Skills you will develop
- Data Science
- Deep Learning
- Mathematical Optimization
- Artificial Neural Network
- Tensorflow
Learn step-by-step
In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:
Create the Neural Network class
Create a forward pass function
Use the cross entropy loss with logits
Create a predict function
Create the main training mechanism and implement gradient descent with automatic differentiation
Break down data-set in batches
Apply the neural network model to solve a multi-class classification problem
Plot the training results
How Guided Projects work
Your workspace is a cloud desktop right in your browser, no download required
In a split-screen video, your instructor guides you step-by-step
Reviews
TOP REVIEWS FROM NEURAL NETWORK FROM SCRATCH IN TENSORFLOW
The instructor has explained each line of code and this helped me understand the context better and I was able to keep track of things with ease. Thank you Sir
It's a nice project where you can implement and understand how a neural network algorithm is built.
Best hands-on experience. The understanding was awesome. Keep making these types of projects.
It's the first time I built the model from scratch instead of using a library, it was fun :)
Frequently asked questions
Frequently Asked Questions
What will I get if I purchase a Guided Project?
Are Guided Projects available on desktop and mobile?
Who are the instructors for Guided Projects?
Can I download the work from my Guided Project after I complete it?
What is the refund policy?
Is financial aid available?
Can I audit a Guided Project and watch the video portion for free?
How much experience do I need to do this Guided Project?
Can I complete this Guided Project right through my web browser, instead of installing special software?
What is the learning experience like with Guided Projects?
More questions? Visit the Learner Help Center.
Coursera Footer
