Dense Associative Memory for Pattern Recognition

Authors: Dmitry Krotov, John J. Hopfield

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The utility of the dense memories is illustrated for two test cases: the logical gate XOR and the recognition of handwritten digits from the MNIST data set. The performance of the proposed classification framework is studied as a function of the power n. The test errors as training progresses are shown in Fig.1B.
Researcher Affiliation Academia Dmitry Krotov Simons Center for Systems Biology Institute for Advanced Study Princeton, USA krotov@ias.edu John J. Hopfield Princeton Neuroscience Institute Princeton University Princeton, USA hopfield@princeton.edu
Pseudocode No No explicitly labeled 'Pseudocode' or 'Algorithm' sections, nor structured code-like blocks were found.
Open Source Code No The paper does not contain any statement about making the source code available or provide a link to a code repository.
Open Datasets Yes The MNIST data set is a collection of handwritten digits, which has 60000 training examples and 10000 test images.
Dataset Splits No The paper refers to a 'validation set' (see the Appendix A in Supplemental) but does not provide explicit split percentages or sample counts in the main text.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory, or detailed computer specifications) used for running experiments are provided.
Software Dependencies No No specific software dependencies with version numbers (e.g., library or solver names with versions) are provided.
Experiment Setup No The paper mentions aspects of the experimental setup such as initialization, activation function choice, optimization method (backpropagation), and memory normalization. It also mentions that hyperparameters were optimized using a validation set, with details in an appendix, but does not provide specific hyperparameter values (e.g., learning rate, batch size) in the main text.