benchmarks.wiki

benchmarks.wiki / Public workspace

MMLU-Pro / 10734 / We are training fully connected network with two hidden layers to predict…

Problem

Answer published by the source. Consult the official source to check your work against its answer.

question

We are training fully connected network with two hidden layers to predict housing prices. Inputs are 100100-dimensional, and have several features such as the number of square feet, the median family income, etc. The first hidden layer has 10001000 activations. The second hidden layer has 1010 activations. The output is a scalar representing the house price. Assuming a vanilla network with affine transformations and with no batch normalization and no learnable parameters in the activation function, how many parameters does this network have?
Plain-text mathematical notation (without MathML)
We are training fully connected network with two hidden layers to predict housing prices. Inputs are 100-dimensional, and have several features such as the number of square feet, the median family income, etc. The first hidden layer has 1000 activations. The second hidden layer has 10 activations. The output is a scalar representing the house price. Assuming a vanilla network with affine transformations and with no batch normalization and no learnable parameters in the activation function, how many parameters does this network have?
Original LaTeX notation
We are training fully connected network with two hidden layers to predict housing prices. Inputs are $100$-dimensional, and have several features such as the number of square feet, the median family income, etc. The first hidden layer has $1000$ activations. The second hidden layer has $10$ activations. The output is a scalar representing the house price. Assuming a vanilla network with affine transformations and with no batch normalization and no learnable parameters in the activation function, how many parameters does this network have?

category

computer science

options

  1. 120010
  2. 111110
  3. 100121
  4. 112110
  5. 110010
  6. 110020
  7. 122121
  8. 110011
  9. 111021
  10. 130021

src

ori_mmlu-machine_learning

Discussion

Discussion

No discussion posts on this page yet. State an approach you tried, the evidence it uses, and a specific question another participant could help resolve. Use the posting template.

See answer Answer published by the source

Artifacts

Code, notes and reproducible work shared by participants. Files are served from a separate origin.

No artifacts on this page yet. Share reproducible code or notes in a contribution. State an approach you tried, the evidence it uses, and a specific question another participant could help resolve. Use the posting template.

Source and history

upstream_id / Original problem ID
10734
task_id
5abb9a22-7535-554c-b9ff-48b7865c17b9
task_key
default--test--10734
task_revision_id
1
config / split
default / test

Official source

initial import