We lifted 7 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| BerenMillidge/Theory_Associative_Memory | canonical | 5 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| gaussian_perturb_image | Ran | BerenMillidge/Theory_Associative_Memory/functions.py code served (permissive licence) · get_code("7dea47c997618e3f") |
| get_id_dictionary | Ran | BerenMillidge/Theory_Associative_Memory/data.py code served (permissive licence) · get_code("f977b3edab4a82bf") |
| halve_continuous_img | Ran | BerenMillidge/Theory_Associative_Memory/functions.py code served (permissive licence) · get_code("1545064ef5ba1b5c") |
| mask_continuous_img | Ran | BerenMillidge/Theory_Associative_Memory/functions.py code served (permissive licence) · get_code("748ea182254b74cd") |
| parse_sname_for_title | Ran | BerenMillidge/Theory_Associative_Memory/plotting.py code served (permissive licence) · get_code("67893413bb7ad279") |
| get_cifar10 | Not yet run | BerenMillidge/Theory_Associative_Memory/data.py code served (permissive licence) · get_code("53ce2056552aef4f") |
| load_mnist | Not yet run | BerenMillidge/Theory_Associative_Memory/data.py code served (permissive licence) · get_code("166095face05d8e0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A large number of neural network models of associative memory have been proposed in the literature. These include the classical Hopfield networks (HNs), sparse distributed memories (SDMs), and more recently the modern continuous Hopfield networks (MCHNs), which possesses close links with self-attention in machine learning. In this paper, we propose a general framework for understanding the operation of such memory networks as a sequence of three operations: similarity, separation, and projection. We derive all these memory models as instances of our general framework with differing similarity and separation functions. We extend the mathematical framework of Krotov et al (2020) to express general associative memory models using neural network dynamics with only second-order interactions between neurons, and derive a general energy function that is a Lyapunov function of the dynamics. Finally, using our framework, we empirically investigate the capacity of using different similarity functions for these associative memory models, beyond the dot product similarity measure, and demonstrate empirically that Euclidean or Manhattan distance similarity metrics perform substantially better in practice on many tasks, enabling a more robust retrieval and higher memory capacity than existing models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.04557")
get_code_for_paper("2202.04557")
have("2202.04557")
Connect an agent — have() is free.