Scribd
Upload
21 views1 page

Assignement 4

Uploaded by

Ahmed Elkerdawy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
21 views1 page

Assignement 4

Uploaded by

Ahmed Elkerdawy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Assignment 4

1. What is the primary difference between a traditional computer program and a neural
network in terms of problem-solving?

2. You have a neural network with three layers: an input layer with 100 neurons, a hidden
layer with 50 neurons, and an output layer with 10 neurons. If each neuron in the hidden
layer is connected to each neuron in the input and output layers, calculate the total number
of weights in the network.

3. Suppose you are training a neural network for image classification with a batch size of 32,
and you have 10,000 training images. How many weight updates will occur during one
epoch (one pass through the entire training dataset)?

4. What is backpropagation, and why is it important in training neural networks?


Programming Assignment: MNIST Image Classification with a Simple Neural Network
Build and train a basic neural network to classify handwritten digits from the MNIST dataset.
Experiment with different hyperparameters to observe their impact on model performance.
Hyperparameters to Experiment With:
• Number of Hidden Layers
• Number of Neurons in Hidden Layers
• Activation Function (e.g., ReLU or Sigmoid)
• Learning Rate
• Batch Size
• Number of Epochs

Training and Evaluation:


• Train the model on the training data with chosen hyperparameters.
• Monitor training metrics.
• Evaluate the model on the test data.
Experimentation:
• Change hyperparameters systematically and observe their effects on model
performance.
• For instance, test different learning rates, layer configurations, or batch sizes.
Reporting:
• Summarize results with tables or charts.
• Discuss how changing hyperparameters impacted the model's performance.

You might also like