Cranium is a portable, header-only, feedforward artificial neural network library written in vanilla C99.
It supports fully-connected networks of arbitrary depth and structure, and should be reasonably fast as it uses a matrix-based approach to calculations. It is particularly suitable for low-resource machines or environments in which additional dependencies cannot be installed.
Cranium supports CBLAS integration. Simply uncomment line 7 in matrix.h to enable the BLAS sgemm function for fast matrix multiplication.
Cross-entropy loss (classification)
Mean squared error (regression)
Batch Gradient Descent
Stochastic Gradient Descent
Mini-Batch Stochastic Gradient Descent
Learning rate annealing
Fan-in weight initialization
CBLAS support for fast matrix multiplication
Simply, click the "Book" button of Cranium and proceed to the payment method. Enter your desired schedule of training. You will receive an email confirmation for Cranium and a representative / trainer will get in touch with you.
|October 22, 2021 (Friday)||09:30 AM - 04:30 PM|
|November 5, 2021 (Friday)||09:30 AM - 04:30 PM|
|November 19, 2021 (Friday)||09:30 AM - 04:30 PM|
|December 3, 2021 (Friday)||09:30 AM - 04:30 PM|
|December 17, 2021 (Friday)||09:30 AM - 04:30 PM|
|December 31, 2021 (Friday)||09:30 AM - 04:30 PM|
|January 14, 2022 (Friday)||09:30 AM - 04:30 PM|
Let us know how we can help you.