We can see that each feature in our observation seems to be on a different scale. Some values range in the hundreds, while others are between 1 and 12, or even binary. While neural networks may still ingest unscaled features, it almost exclusively prefers to deal with features on the same scale. In practice, a network can learn from heterogeneously scaled features, but it may take much longer to do so without any guarantee of finding an ideal minimum on the loss landscape. To allow our network to learn in an improved way for this dataset, we must homogenize our data through the process of feature-wise normalization. We can achieve this by subtracting the feature-specific mean and dividing it by the feature-specific standard deviation for each feature in our dataset. Note that in live-deployed models (for the stock exchange, for example), such a scaling...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from Hands-On Neural Networks with Keras
Niloy Purkait is a technology and strategy consultant by profession. He currently resides in the Netherlands, where he offers his consulting services to local and international companies alike. He specializes in integrated solutions involving artificial intelligence, and takes pride in navigating his clients through dynamic and disruptive business environments. He has a masters in Strategic Management from Tilburg University, and a full specialization in data science from Michigan University. He has advanced industry grade certifications from IBM, in subjects like signal processing, cloud computing, machine and deep learning. He is also perusing advanced academic degrees in several related fields, and is a self-proclaimed lifelong learner.
Read more about Niloy Purkait
Unlock this book and the full library FREE for 7 days
Author (1)
Niloy Purkait is a technology and strategy consultant by profession. He currently resides in the Netherlands, where he offers his consulting services to local and international companies alike. He specializes in integrated solutions involving artificial intelligence, and takes pride in navigating his clients through dynamic and disruptive business environments. He has a masters in Strategic Management from Tilburg University, and a full specialization in data science from Michigan University. He has advanced industry grade certifications from IBM, in subjects like signal processing, cloud computing, machine and deep learning. He is also perusing advanced academic degrees in several related fields, and is a self-proclaimed lifelong learner.
Read more about Niloy Purkait