Dataset Viewer
Auto-converted to Parquet Duplicate
data_source
stringclasses
1 value
prompt
listlengths
1
1
ability
stringclasses
1 value
reward_model
dict
extra_info
dict
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\nBars problem for RBM training -- the canonical Hinton 2000 / Foldiak 1990\nsanity check for contrastive divergence.\n\nProblem:\n Generate 4x4 binary images by independently activating each of 8 possible\n bars (4 horizontal rows + 4 vertical columns) with a small prob...
{ "slug": "bars-rbm", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/bars-rbm/bars_rbm.py" }
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\nMNIST-2x5 subclass distillation.\n\nReproduction of the central experiment from Mueller, Kornblith & Hinton,\n\"Subclass distillation\", arXiv:2002.03936 (2020).\n\nSetup\n-----\n- Re-label MNIST: digits 0..4 -> super-class A, digits 5..9 -> super-class B.\n- The TEACHER...
{ "slug": "mnist-2x5-subclass", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/mnist-2x5-subclass/mnist_2x5_subclass.py" }
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\nGrapheme-sememe synthetic word reading + lesion / relearning experiments.\n\nSource:\n Hinton & Sejnowski (1986), \"Learning and relearning in Boltzmann machines\",\n in Rumelhart & McClelland (eds.), *Parallel Distributed Processing*, Vol. 1,\n Chapter 7.\n\nPr...
{ "slug": "grapheme-sememe", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/grapheme-sememe/grapheme_sememe.py" }
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\nFast weights to deblur old memories (Hinton & Plaut 1987).\n\nSource:\n G. E. Hinton and D. C. Plaut (1987), \"Using Fast Weights to Deblur Old\n Memories\", Proceedings of the Ninth Annual Conference of the Cognitive\n Science Society, pp. 177-186.\n\nProblem:\...
{ "slug": "fast-weights-rehearsal", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/fast-weights-rehearsal/fast_weights_rehearsal.py" }
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\nHelmholtz-machine shifter (Dayan, Hinton, Neal & Zemel 1995, \"The Helmholtz\nmachine\", Neural Computation 7(5):889--904).\n\nProblem:\n 4 x 8 binary image. Row 0 (and its duplicate row 1) is uniform-Bernoulli with\n marginal p_on=0.2. Rows 2-3 (duplicates) are row 0 ...
{ "slug": "helmholtz-shifter", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/helmholtz-shifter/helmholtz_shifter.py" }
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\n8-3-8 backprop autoencoder -- backprop mirror of Ackley/Hinton/Sejnowski (1985)\nencoder, trained the way Rumelhart, Hinton & Williams (1986) trained their\nMLPs in \"Learning internal representations by error propagation\" (PDP Vol. 1,\nCh. 8).\n\nProblem:\n 8 one-hot ...
{ "slug": "encoder-backprop-8-3-8", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/encoder-backprop-8-3-8/encoder_backprop_8_3_8.py" }
hinton_problems
[ { "role": "user", "content": "Implement the following learning problem from scratch in pure NumPy. Produce a single self-contained Python file containing the dataset, the model, the training loop, and an evaluation that prints the headline metric. The implementation must run on a laptop CPU in under five mi...
code
{ "style": "model", "ground_truth": "\"\"\"\n4-3-4 encoder -- over-complete Boltzmann-machine reproduction from\nAckley, Hinton & Sejnowski, \"A learning algorithm for Boltzmann machines\",\nCognitive Science 9 (1985).\n\nProblem:\n Two groups of 4 visible binary units (V1, V2) connected through 3 hidden\n binary...
{ "slug": "encoder-4-3-4", "file": "/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/encoder-4-3-4/encoder_4_3_4.py" }
hinton_problems
[{"role":"user","content":"Implement the following learning problem from scratch in pure NumPy. Prod(...TRUNCATED)
code
{"style":"model","ground_truth":"\"\"\"AIR (Attend, Infer, Repeat) on Multi-MNIST scenes -- pure num(...TRUNCATED)
{"slug":"air-multimnist","file":"/Users/anton/source/extropic/_posttraining/data_source/hinton-probl(...TRUNCATED)
hinton_problems
[{"role":"user","content":"Implement the following learning problem from scratch in pure NumPy. Prod(...TRUNCATED)
code
{"style":"model","ground_truth":"\"\"\"\n4-2-4 encoder — Boltzmann-machine reproduction of the exp(...TRUNCATED)
{"slug":"encoder-4-2-4","file":"/Users/anton/source/extropic/_posttraining/data_source/hinton-proble(...TRUNCATED)
hinton_problems
[{"role":"user","content":"Implement the following learning problem from scratch in pure NumPy. Prod(...TRUNCATED)
code
{"style":"model","ground_truth":"\"\"\"\nBars task — Helmholtz machine + wake-sleep reproduction o(...TRUNCATED)
{"slug":"bars","file":"/Users/anton/source/extropic/_posttraining/data_source/hinton-problems/bars/b(...TRUNCATED)
End of preview. Expand in Data Studio

No dataset card yet

Downloads last month
52