I am designing the ANN code for my dataset (which is actually regressor type problem having 3 IDV and 1 DV).I am getting a good accuracy but i couldn't find the code to predict any single value like we predict in Random forest and in decision tree.So,suggest me the way to predict any value which can also might lies in between the given values.
In an Artificial Neural Network (ANN) for a regression problem, we can use the trained model to predict a single value for a given set of independent variables (features). The ANN's predicted value can lie between the shared values since regression deals with continuous numerical values rather than discrete classes.
Here's an example of how you can predict a single value using a trained ANN model in Python using the Keras library:
import numpy as np
from keras.models import load_model
# Load the trained ANN model
model = load_model('trained_ann_model.h5')
# Sample input data for prediction (replace this with your actual data)
sample_input = np.array([[feature1_value, feature2_value, feature3_value]])
# Make predictions
predicted_value = model.predict(sample_input)
print("Predicted Value:", predicted_value[0][0])
In this example, replace trained_ann_model.h5 with the path to your saved trained ANN model. sample_input should be a NumPy array containing the input values for the three independent variables (feature1_value, feature2_value, feature3_value). The model.predict() function will provide the expected value for the dependent variable (target variable) based on the input data.
Once the trained model is ready, it can be used to predict single values or make predictions on new data points for regression problems.
sir can you please share your whatsapp or contact no.? Mrutyunjaya Hiremath
import tensorflow as tf import numpy as np # Define the input data and target values X_train = np.array([[0.1, 0.2, 0.3], [0.4, 0.5, 0.6], [0.7, 0.8, 0.9]]) # Input features y_train = np.array([0.3, 0.6, 0.9]) # Target values # Define the model architecture model = tf.keras.Sequential([ tf.keras.layers.Dense(16, activation='relu', input_shape=(3,)), tf.keras.layers.Dense(8, activation='relu'), tf.keras.layers.Dense(1) ]) # Compile the model model.compile(optimizer='adam', loss='mean_squared_error') # Train the model model.fit(X_train, y_train, epochs=100, batch_size=1) # Perform single-value prediction X_test = np.array([[0.2, 0.3, 0.4]]) # Input for prediction prediction = model.predict(X_test) print("Prediction:", prediction[0])
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Programming Languages
- Python