Learn about the programming interface Keras provides for defining neural networks.
- [Instructor] Keras makes it very straightforward…to code neural networks.…A neural network is a machine-learning algorithm…made up of individual nodes called neurons.…These nodes, or neurons, are arranged…into a series of groups called layers.…Nodes in each layer are connected…to nodes in the following layer.…Data flows from the input to the output…along these connections.…Each individual node is trained to perform…a simple mathematical calculation and then feed its data…to all the nodes it's connected to.…
When many trained nodes are connected and data flows…through the entire network from start to finish,…neural networks are able to model complex operations.…When designing a neural network in Keras,…we have to decide how many layers there should be,…how many nodes should be in each layer…and how the layers should be connected to each other.…Bigger models with more layers and more nodes…can model more complex operations,…but if you make the model too big, it will beslow the train…and is likely to overfit the data set.…
Released
8/1/2017- What's Keras?
- Using Keras vs. TensorFlow
- Training a deep learning model
- Using a pre-trained deep learning model
- Monitoring a Keras model with TensorBoard
- Using a trained Keras model in Google Cloud
Share this video
Embed this video
Video: Keras Sequential API