Move on from what you learned from studying the principles of recurrent neural networks, and how they can solve problems involving sequencing, with this cohesive course on Improving Performace. Learn to improve the performance of your neural networks by starting with learning curves that allow you to answer the right questions. This could be needing more data or, even, building a better model to improve your performance.
Further into the course, you will explore the fundamentals around bash normalization, drop-out, and regularization.
This course also touches on data augmentation and its ability to allow you to build new data from your starting training data, culminating in hyper-parameter optimization. This is a tool to that aids in helping you to decide how to tune the external parameters of your network.
This course is made up of 13 lectures and three accompanying exercises. This Cloud Academy course is in collaboration with Catalit.
- Learn how to improve the performance of your neural networks.
- Learn the skills necessary to make executive decisions when working with neural networks.
- It is recommended to complete the Introduction to Data and Machine Learning course before starting.
Hey guys. Welcome back. In this video, we're going to review exercise three in section nine. Exercise three is actually pretty long and complex and it should give you plenty of what a real world scenario is. So, feel free to look at this solution if you feel lost. It is quite a long and complex exercise. And most likely, you will have to perform it on a GPU. So, the data is provided as a ZIP file and it was obtained and repackaged from a data set, that is public available on Crowdflower. It's a set of pictures of males and females and we're going to build an image classifier, that will recognize the gender of a person from pictures.
So, first thing you gotta do is download the data and have a look at the directory structure and inspect a couple of pictures, in order to understand what they look like. Then, design a model, that will take a color image of size 64 by 64 as input and return a binary output. Female equals zero and male equals one. Feel free to introduce any regularization technique, Dropout, Batch Normalization, Weight Regularization, whatever you prefer. Then compile your model with an optimizer of your choice. And then, feed the data using an image generator, that will transform and augment your data with a transformation of your choice and flow the data from the directory in batches. So, this uses components, that we've used before, but it combines them together in a way. Also, use the fit generator function to fit the model on the batches generated from the generator. And finally, once you're satisfied with your training, check a few misclassified pictures and ask yourself if the errors, the model made, makes sense. A long exercise, but I am sure you at least will try it. So, thank you for watching and good luck.
I am a Data Science consultant and trainer. With Catalit I help companies acquire skills and knowledge in data science and harness machine learning and deep learning to reach their goals. With Data Weekends I train people in machine learning, deep learning and big data analytics. I served as lead instructor in Data Science at General Assembly and The Data Incubator and I was Chief Data Officer and co-founder at Spire, a Y-Combinator-backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. I earned a joint PhD in biophysics at University of Padua and Université de Paris VI and graduated from Singularity University summer program of 2011.