reproducibilityindex.ai

Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs

Authors: Li Jing, Yichen Shen, Tena Dubcek, John Peurifoy, Scott Skirlo, Yann LeCun, Max Tegmark, Marin Soljačić

Reproducibility Variable	Result	LLM Response
Research Type	Experimental	Finally, we test the performance of EUNNs on the standard copying task, the pixelpermuted MNIST digit recognition benchmark as well as the Speech Prediction Test (TIMIT).
Researcher Affiliation	Collaboration	1Massachusetts Institute of Technology 2New York University, Facebook AI Research.
Pseudocode	Yes	Algorithm 1 Efﬁcient implementation for F with parameter θi and φi.
Open Source Code	Yes	All models are implemented in both Tensorﬂow and Theano, available from https://github.com/ jingli9111/EUNN-tensorflow and https: //github.com/iguanaus/EUNN-theano.
Open Datasets	Yes	We use the TIMIT dataset (Garofolo et al., 1993) sampled at 8 k Hz.
Dataset Splits	Yes	We trained all ﬁve RNNs for T = 1000 with the same batch size 128 using RMSProp optimization with a learning rate of 0.001. The decay rate is set to 0.5 for EURNN, and 0.9 for all other models respectively.
Hardware Specification	No	The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used for the experiments.
Software Dependencies	No	The paper mentions that models are implemented in 'Tensorﬂow' and 'Theano' but does not specify their version numbers.
Experiment Setup	Yes	We trained all ﬁve RNNs for T = 1000 with the same batch size 128 using RMSProp optimization with a learning rate of 0.001. The decay rate is set to 0.5 for EURNN, and 0.9 for all other models respectively.