model = LSTMByHand()
print("\nComparing observed and predicted values")
print(
"Company A: Observed = 0, Predicted =",
model(torch.tensor([0., 0.5, 0.25, 1.])).detach()
)
print(
"Company B: Observed = 1, Predicted =",
model(torch.tensor([1., 0.5, 0.25, 1.])).detach()
)
Here, we pass a tensor containing the stock prices for Days 1 through 4. The model then predicts the value for Day 5.
The model returns both the prediction and its associated computation graph. We call .detach() to remove the computation graph and retrieve only the prediction.
Running the code produces the following output:
Comparing observed and predicted values
Company A: Observed = 0, Predicted = tensor(-0.2321)
Company B: Observed = 1, Predicted = tensor(-0.2360)
The prediction for Company A is reasonably close to the observed value.
However, the prediction for Company B is quite far from the expected value.
In the next article, we will train the model to improve these predictions.
AI agents write code fast. They also silently remove logic, change behavior, and introduce bugs -- without telling you. You often find out in production.
git-lrc fixes this. It hooks into git commit and reviews every diff before it lands. 60-second setup. Completely free.
Any feedback or contributors are welcome! It's online, source-available, and ready for anyone to use.
Give it a β star on Github