McqMate

Neural Network - Question and answers

I'm working on a neural network for time series forecasting using LSTM, but my predictions are consistently lagging behind the actual data. How can I fix this issue?

Neural Network lstm time-series-forecasting

I've implemented an LSTM model in TensorFlow with two layers, each with 50 units, and I'm using a sequence length of 10 steps to predict the next value. The data is normalized, and I've split it into 70/30 train-test sets. I've tried adjusting batch sizes from 32 to 128 and learning rates from 0.01 to 0.0001, but the lag persists. Any advice on improving the model's timing would be great!

LP

Liam Patel

1 week ago
I'm building a recommendation system using a neural network, and I'm struggling with how to handle sparse user-item interaction data efficiently. What are the best practices for preprocessing and modeling this?

Neural Network recommendation-system data-preprocessing

I'm working on a project for an e-commerce site where I need to recommend products based on user purchase history. The interaction matrix is very sparse (most users have only a few interactions), and I'm using collaborative filtering with a neural network in PyTorch. I've tried using embedding layers, but the model isn't learning well, and training is slow. I've already normalized the data and split it into train/val sets. What should I focus on to improve performance?

PS

Priya Sharma

2 days ago