Trending

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Bookmarked byJesse

Machine Learning

Neural and Evolutionary Computing

Stats Machine Learning

MNIST-1D: A Simple, Low-Memory, and Low-End Benchmark for Deep Learning

Scaling *down* Deep Learning

We introduce a minimalist, low-memory, and low-compute alternative to classic deep learning benchmarks.

The training examples are 20 times smaller than classic benchmarks yet they differentiate more clearly between linear, nonlinear, and convolutional models which attain 32, 68, and 94% accuracyrespectively (these models obtain 94, 99+, and 99+% on mnist).

Then we present example use cases which include measuring the spatial inductive biases of lottery tickets, observing deep double descent, and metalearning an activation function.

Authors

Sam Greydanus

Related Topics

Deep learning models

Activation function

Deep double descent

Linear, nonlinear, and convolutional models

Read the Paper

Read Paper

Trending

Bookmarks

◐ Recommended Follows

Mohammadreza Rezaee

Dr Rockson Samuel

Madhu Mithra K K

Justin Dicaprio

More

◐ Latest Activity

More

MNIST-1D: A Simple, Low-Memory, and Low-End Benchmark for Deep Learning - 42Papers

Read Related Papers

Multi-Scale Deep Learning for Estimating Horizontal Velocity Fields on the Solar Surface

Data Selection Based Fine-tuning Pipeline for Image Classification

Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks

Adversarial AutoAugment

Softmax Gradient Tampering: Decoupling the Backward Pass for Improved Fitting

Accelerating Deep Learning with Dynamic Data Pruning

Disparity Between Batches as a Signal for Early Stopping

8-bit approximation of softmax layer in multi-layer perceptron oral neural networks

Finding the Winning Ticket of BERT for Binary Text Classification via Adaptive Layer Truncation before Fine-tuning

A Framework to Plant and Hide Extremely Sparse Network Topologies