Understanding RNNs: Neural Networks for Time-Dependent Data

#machinelearning #ai

In my previous articles, we have explored neural networks and related concepts.

Now let's explore another example use-case.

The stock price problem

When we look at stock prices, they tend to change over time.

Example: the price of a stock increased for 4 days straight, then it went down.

The longer a company has been traded on the stock market, the more data we will have for it.

So if we want to use a neural network to predict stock prices, then we need a neural network that works with different amounts of sequential data.

In other words, if we want to predict the stock price for the company (active since day 1) on day 10, then we need to use the data for the 9 preceding days.

In contrast, if we need to predict the price for the company (active since day 5) on day 10, then we would only have data for the preceding 5 days.

So we need to make the neural network flexible in terms of how much sequential data we use to make a prediction.

This is a big difference compared to other neural networks.

One way to deal with the problem of having different amounts of input values is to use a Recurrent Neural Network (RNN).

Just like other neural networks, RNNs have weights, biases, layers, and activation functions.

The big difference is that recurrent neural networks also have feedback loops.

Although the neural network looks like it is taking a single input value, the feedback loop makes it possible to use sequential input values, like stock market prices collected over time, to make predictions.

To understand exactly how this RNN can make predictions with sequential input values, we have to run some data through it, which we will explore in the next article.

Looking for an easier way to install tools, libraries, or entire repositories?
Try Installerpedia: a community-driven, structured installation platform that lets you install almost anything with minimal hassle and clear, reliable guidance.

Just run: