Python Dictionaries: Not even a space-time tradeoff If you could choose to store things that you’d want to look up later in a Python dictionary or in a Python list, which would you choose? It turns out that looking up items in a Python dictionary is much faster than looking up items in a Python list. If you search for … Read More
Numpy Views vs Copies: Avoiding Costly Mistakes
In this post we will talk about the differences between views and copies. It’s really important you’re aware of the difference between the two. Otherwise you might run into problems like accidentally modifying arrays. What are views and copies? With a view, it’s like you are viewing the original (base) array. The view is actually part of the original array even though … Read More
LSTMs for Time Series in PyTorch
I can’t believe how long it took me to get an LSTM to work in PyTorch! There are many ways it can fail. Sometimes you get a network that predicts values way too close to zero. In this post, we’re going to walk through implementing an LSTM for time series prediction in PyTorch. We’re going to use pytorch’s nn module … Read More
Generating Autoregressive data for experiments
In this post, we will go through how to generate autoregressive data in Python, which is useful for debugging models for sequential prediction like recurrent neural networks. When you’re building a machine learning model, it’s often helpful to check that it works on simple problems before moving on to complicated ones. I’ve found this is especially useful for debugging neural … Read More