You have a tensor x = torch.tensor([1, 2, 3, 4]).
You perform
stacked_x_dim0 = torch.stack([x, x, x], dim=0)And
stacked_x_dim1 = torch.stack([x, x, x], dim=1)What will be the shapes of stacked_x_dim0 and stacked_x_dim1 respectively?
stacked_x_dim0: [3, 3], stacked_x_dim1: [4, 4]
stacked_x_dim0: [4, 3], stacked_x_dim1: [3, 4]
stacked_x_dim0: [3, 4], stacked_x_dim1: [4, 3]
stacked_x_dim0: [4, 4], stacked_x_dim1: [3, 3]
You have a PyTorch tensor
gpu_tensor = torch.tensor([1, 2, 3]).to('cuda')residing on the GPU. You then attempt to convert it directly to a NumPy array using
numpy_array = gpu_tensor.numpy()What will be the outcome of this operation?
It will successfully convert gpu_tensor to a NumPy array on the CPU.
It will successfully convert gpu_tensor to a NumPy array that also resides on the GPU.
It will raise a RuntimeError because NumPy arrays cannot directly operate on GPU memory.
It will create a view of the gpu_tensor on the CPU without copying data.
The numpy() method is not available for GPU tensors.
The Huber Loss function is introduced as a robust alternative to Mean Squared Error (MSE) and Mean Absolute Error (MAE). What is the primary characteristic of Huber Loss that makes it robust to outliers?
It always produces a gradient of zero for all errors, preventing large updates.
It exclusively uses a quadratic penalty, but only for errors exactly at the threshold.
It transitions from a quadratic loss for small errors to a linear loss for large errors, thereby down-weighting the impact of outliers.
It entirely ignores errors beyond a certain delta, considering them irrelevant.
It applies a logarithmic transformation to all error values before computing the loss.
Sign in with Google — it is free — to see every question with its answer and explanation, practise it in learning mode, or take it as a timed mock test.
The IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 2 paper sat on 23 Nov 2025, in the September 2025 term: 25 questions for 50 marks in 120 minutes. The first 3 questions are below. Sign in with Google — it is free — to see the whole paper with its answers and explanations, in learning mode or as a timed mock test.
| Feature | Deep Learning and GenAI Quiz 2 23 Nov 2025 at a glance |
|---|---|
| Term | September 2025 term |
| Subject | Introduction to Deep Learning and Generative AI |
| Course code | BSDA2001 |
| Questions | 25 |
| Marks | 50 |
| Duration | 120 min |
| MCQ | 17 |
| Numerical | 7 |
| MSQ | 1 |
| Official paper | IIT M DIPLOMA AN EXAM QDD2 23 Nov 2025 NEW |
| Negative marking | No negative marking. |
| Updated |