Skip to main content

High level GPU simulations of low level device characteristics in ML algorithms

Project description

Welcome to LowPy (Pre-release)!

LowPy is a high level GPU simulator of low level device characteristics in machine algorithms. It seeks to streamline the investigation process when considering memristive and other novel devices for implementing a machine learning algorithm in hardware. By using the familiar Keras syntax, it will be second nature to write GPU-optimized code to push your algorithm to its limits.

Features

The aim is to focus first on the algorithms most published on in the field of neuromorphic computing, for both static and time series datasets.

Datasets

  • MNIST

Algorithms

  • Single Layer Perceptron (SLP)
  • Multi-Layer Perceprton (MLP)

Activation Functions

  • Sigmoid

Optimization Functions

  • Stochastic Gradient Descent (SGD)
  • SGD with Momentum

Initialization Distributions

  • Uniform
  • Normal

Device Characteristics

  • Write Variability

Requirements

The following are required to use LowPy:

  • GPU: NVIDIA
  • OS: Linux (should work on Windows, not tested)
  • Python 3.0 or newer
  • PyCUDA

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lowpy-0.1.6.tar.gz (7.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

lowpy-0.1.6-py3-none-any.whl (7.5 kB view details)

Uploaded Python 3

File details

Details for the file lowpy-0.1.6.tar.gz.

File metadata

  • Download URL: lowpy-0.1.6.tar.gz
  • Upload date:
  • Size: 7.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.22.0 setuptools/51.3.3 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.5

File hashes

Hashes for lowpy-0.1.6.tar.gz
Algorithm Hash digest
SHA256 d810e9d6e09e8dca55ca912872051827df6efbc25d33446f90878e11a225ae69
MD5 6780b4d842d07359f5044ac839580535
BLAKE2b-256 8469eb4476f71bb7cc529b5061e6cf61a7d5721ae87c5f6abada1ac6ec2abeb3

See more details on using hashes here.

File details

Details for the file lowpy-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: lowpy-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 7.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.22.0 setuptools/51.3.3 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.5

File hashes

Hashes for lowpy-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 8bf629fb6d34a4588587e5b00ea105032e0afc382a529bd427e760f331e76e9f
MD5 c5df654b91d7d2ad79570770fdcddfdc
BLAKE2b-256 52817c7fea89ecf744293f72fb081706427b1724c073b02606f3ab5af5cb693f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page