Responses for Day 2, July 7

1. Traditional programming consists of inputting data and creating rules for a model to follow, and then getting answers in return. Machine learning, however, takes answers and data as an input and the model creates (or, perhaps more appropriately, guesses) the rules.
2. The model first predicted 22.000134 for an input of 7. Running it again, the model got a predicted value of 21.996933. Although these values are incredibly close, they are still different, which is due to the stochastic or random nature of neural networks.
3. According to the model (trained on the new house data), the Church St home is the most overvalued (and is therefore the worst deal) at 99k over model price (300k). The best buy would be Holly Point which is undervalued at 138k below model price (235k).