Image Recognition Using CNN

123456789101112
Across
  1. 4. One complete pass through the entire training dataset.
  2. 5. Learning technique that adapts a pre-trained model to a new task.
  3. 6. Another term for fully connected layers in neural networks.
  4. 7. Another term for the filter used in convolutional layers.
  5. 8. Descent optimization algorithm used to minimize the loss function
  6. 10. Function applied to neurons to introduce non-linearity (e.g., ReLU).
  7. 11. Type of layer in CNN that extracts features from the input image.
  8. 12. A commonly used pre-trained CNN model.
Down
  1. 1. Layer in CNN that reduces the spatial dimensions of feature maps.
  2. 2. Layer that converts pooled feature maps into a single-dimensional vector.
  3. 3. Simplest artificial neural network consists of a single layer of neurons.
  4. 9. Large dataset often used to pre-train CNN models.