Penny is an artificial intelligence system that relies on satellite imagery to predict income levels in your neighborhood. If you want to know whether the area you want to move in has the potential to support economic growth or not, this tool may come in handy.
You can play around with the landscape of a city or a particular city region by adding and removing various urban features such as buildings, parks, shopping centers and see how these items will influence the wealth of the respective area.
Penny was trained by overlaying census data on high-resolution satellite images of New York. The AI’s neural network quickly identified visual patterns in the landscape and correlated them with income. For example, the AI system correlated parking lots with low income, and green spaces with high income.
There are also instances where Penny uses some sort of an intuition. In other words, adding high income symbols in a low-income neighborhood doesn’t convince it that the respective area is wealthy. This counterintuitive behavior is quite surprising. Penny learnt that certain features are synonym for wealth, but it appears that sometimes the system simply decides to drop those criteria and make a counterintuitive prediction.
Play with Penny and test the system’s limits
Penny also features an interesting interface that lets you play with the neural network’s patterns. For example, you can place apartment buildings in various areas of New York and watch how that affects Penny’s predictions. The buildings will have a completely different effect depending on where you choose to place them.
Penny’s creators hope that this AI tool will spark a conversation about AI, machine learning, and big data.
“How machines understand these things has increasingly important implications for how we understand patterns of urbanization, wealth, and the human condition“, they say.
You can play around with Penny on the tool’s official website.
YOU MAY ALSO LIKE: OpenAI creates new AI algorithm that shapes the learning of other AI agentsFollow The AI Center on social media:
Join me as I track the latest progress in AI research.
Latest posts by Maddie Blau (see all)
- AI helps researchers improve gene editing results - January 13, 2018
- True Emoji is an AI app that uses your expressions to create animated emojis - November 21, 2017
- Canada’s first AI exchange-traded fund enters the market - November 2, 2017