LSTM Interpretability: A Practical Tutorial

A practical tutorial on LSTM interpretability demonstrates how to preprocess time-series data into a 3D tensor, build a stacked LSTM model with dropout and early stopping, and apply permutation importance to identify which lag days most influence forecasts. The tutorial uses weather data and Keras to show that skipping MinMaxScaler can cause exploding gradients, and that return_sequences=True is mandatory when stacking LSTM layers.

LSTM Interpretability: A Practical Tutorial 1. Data Preprocessing for Time Series LSTMs require a 3D tensor input formatted as samples, timesteps, features . To handle this, you have to transform flat temperature columns into overlapping windows. python import numpy as np import pandas as pd from sklearn.preprocessing import MinMaxScaler 1. Load data df = pd.read csv "weather data.csv" data = df 'Temperature' .values.reshape -1, 1 2. Scale the data for stable neural network training scaler = MinMaxScaler feature range= 0, 1 scaled data = scaler.fit transform data 3. Create sequences: 7 days of lag to predict the 8th day X, y = , for i in range 7, len scaled data : X.append scaled data i-7:i y.append scaled data i X, y = np.array X , np.array y print f"Input shape: {X.shape}" Output: Samples, 7, 1 Skipping the MinMaxScaler is a common mistake; without it, LSTMs are highly susceptible to exploding gradients, which can crash your training process. 2. Model Architecture and Deployment I use a stacked LSTM approach with dropout to prevent overfitting. A critical technical detail here is the return sequences=True parameter on the first layer, which is mandatory when stacking LSTMs so the second layer receives the full sequence of hidden states. python from tensorflow.keras.models import Sequential from tensorflow.keras.layers import LSTM, Dense, Dropout, Input from tensorflow.keras.callbacks import EarlyStopping 1. Build the network model = Sequential Input shape= 7, 1 , LSTM units=100, activation='relu', return sequences=True , Dropout 0.2 , LSTM units=100, activation='relu' , Dropout 0.2 , Dense units=1 model.compile optimizer='adam', loss='mse' 2. Configure Early Stopping early stopping = EarlyStopping monitor='val loss', patience=10, restore best weights=True 3. Train the model history = model.fit X, y, epochs=50, batch size=32, validation split=0.2, callbacks= early stopping 3. Applying XAI Methods To move beyond the black box, we can use permutation importance. This method identifies which "lag day" the model values most by shuffling the data for a specific day and measuring the resulting spike in error. python from sklearn.metrics import mean squared error base preds = model.predict X, verbose=0 base error = mean squared error y, base preds feature importance = for i in range 7 : X permuted = X.copy np.random.shuffle X permuted :, i, 0 Shuffle a specific lag day permuted preds = model.predict X permuted, verbose=0 permuted error = mean squared error y, permuted preds feature importance.append permuted error - base error By calculating the difference between the permuted error and base error , you can pinpoint exactly which days in the 7-day window are driving the forecast. For a deeper dive into AI workflows, check out the resources at promptcube3.com. Next Hardening AI-generated code for legacy systems: A practical guide → /en/threads/3298/