Code, Explained: Training a model in TensorFlow

Jessica YungArtificial Intelligence, Self-Driving Car ND

In a previous post, we went through the TensorFlow code for a multilayer perceptron. Now we will discuss how we train the model with TensorFlow, specifically in a TensorFlow Session. We will use Aymeric Damien’s implementation in this post. I recommend you skim through the code first and have the code open in a separate window. I have included the key portions … Read More

Explaining TensorFlow code for a Multilayer Perceptron

Jessica YungHighlights, Programming, Self-Driving Car ND

In this post we go through the code for a multilayer perceptron in TensorFlow. We will use Aymeric Damien’s implementation. I recommend you have a skim before you read this post. I have included the key portions of the code below. 1. Code Here are the relevant network parameters and graph input for context (skim this):

Here is the model … Read More

Comparing Model Performance with Normalised vs standardised input (Traffic Sign Classifier)

Jessica YungData Science, Self-Driving Car ND, Statistics

In the previous post, we explained (1) what normalisation and standardisation of data were, (2) why you might want to do it and (3) how you can do it. In this post, we’ll compare the performance of one model on unprocessed, normalised and standardised data. We’d expect using normalised or standardised input to give us higher accuracy, but how much better … Read More

Traffic Sign Classifier: Normalising Data

Jessica YungSelf-Driving Car ND, Statistics

In this post, we’ll talk about (1) what normalising data is, (2) why you might want to do it, and (3) how you can do it (with examples). Background: The Mystery of the Horrifically Inaccurate Model Let me tell you a story. Once upon a time, I trained a few models to classify traffic signs for Udacity’s Self-Driving Car Nanodegree. I first … Read More

18 Game Theory Ideas

Jessica YungEconomics

Image creds: SMBC Here are 18 game theory-related ideas I came up with in the last Game Theory lecture of term. These are things that I think would be interesting to explore and are suited to (but do not require) people who have elementary knowledge of game theory. Look into Quantum game theory. Create a game theory problems tree. E.g. … Read More

How to use AWS EC2 GPU instances with BitFusion

Jessica YungData Science, Uncategorized

If you want to train neural networks seriously, you need more computational power than the typical laptop has. There are two solutions: Get (buy or borrow) more computational power (GPUs or servers) or Rent servers online. GPUs cost over a hundred dollars each and top models like the NVIDIA TESLA cost thousands, so it’s usually easier and cheaper to rent … Read More

Eradicating Unemployment with On-Demand Services?

Jessica YungEconomics

This week our Macroeconomics lecturer suggested that on-demand services such as Uber and TaskRabbit might eradicate unemployment. He claimed figures showed that unemployed people spent only two hours a week on average looking for jobs, so with Uber etc. they could earn money and work while still having enough time to look for new jobs they’d like to move on … Read More

Programming Problem Patterns #1

Jessica YungProgramming

Want to know common patterns in programming problems and mistakes people might make? Then this series is for you. In these posts I will document my main takeaways from doing programming problems and mistakes I make, whether they be outright errors or suboptimal code chunks. Each post has two parts: the problem statement and notes. I may include the solution … Read More