The Successor Representation #1: Generalising between states

Jessica YungMachine Learning

In this post we will discuss a way of representing a state that has exciting connections with how our brain seems to work. First, we’ll briefly look at some foundational ideas (representation and generalisation). Next, we’ll introduce the Successor Representation (SR), which is motivated by finding a representation that generalises across states, and that might be useful in reinforcement learning. … Read More

LSTMs for Time Series in PyTorch

Jessica YungMachine Learning, Uncategorized

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

Jessica YungData Science, Machine Learning

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

What makes Numpy Arrays Fast: Memory and Strides

Jessica YungMachine Learning, Programming

How is Numpy so fast? In this post we find out how Numpy’s ndarray is stored and how it is usually manipulated by Numpy functions using strides. Getting to know the ndarray A NumPy ndarray is a N-dimensional array. You can create one like this:

These arrays are homogenous arrays of fixed-sized items. That is, all the items in … Read More

MSE as Maximum Likelihood

Jessica YungMachine Learning

MSE is a commonly used error metric. But is it principly justified? In this post we show that minimising the mean-squared error (MSE) is not just something vaguely intuitive, but emerges from maximising the likelihood on a linear Gaussian model. Defining the terms Linear Gaussian Model Assume the data is described by the linear model , where . Assume is … Read More

Maximum Likelihood as minimising KL Divergence

Jessica YungMachine Learning

Sometimes you come across connections that are simple and beautiful. Here’s one of them! What the terms mean Maximum likelihood is a common approach to estimating parameters of a model. An example of model parameters could be the coefficients in a linear regression model , where is Gaussian noise (i.e. it’s random). Here we choose parameter values that maximise the … Read More

RNNs as State-space Systems

Jessica YungEngineering, Machine Learning

It’s fantastic how you can often use concepts from one field to investigate ideas in another area and improve your understanding of both areas. That’s one of the things I enjoy most. We’ve just started studying state-space models in 3F2 Systems and Control (a third-year Engineering course at Cambridge). It’s reminded me strongly of recurrent neural networks (RNNs). Look at … Read More

Effective Deep Learning Resources: A Shortlist

Jessica YungArtificial Intelligence, Data Science, Education, Machine Learning, Studying

A lot of people ask me how to get started with deep learning. In this post I’ve listed a few resources I recommend for getting started. I’ve only chosen a few because I’ve found precise recommendations to be more helpful. Let me know if you have any comments or suggestions! Prelude: If you’re new to machine learning Deep learning is … Read More