Realization
- Baptiste Wicht
- Contact: Jean Hennebert
Keywords
- Machine Learning
- Deep Learning
- Neural Networks
- High-Performance
- Industrial grade software
- C++
Our skills
Machine Learning algorithms
High-Performance
Machine Learning framework for C++
DLL is a machine learning framework that aims to provide a C++ implementation of neural networks and convolutional neural networks. The implementation provides significant speedups on cpu in comparison to other frameworks such as TensorFlow or Torch. It is then dedicated to the use phase of such deep models where performance on cpu is requested, such as in industry 4.0 applications.
The framework is highly optimized for CPU computations and also includes a prototype with accelerated GPU support.
Features
- Artificial Neural Network (ANN)
- Convolutional Neural Network (CNN)
- Stochastic Gradient Descent optimization
- Conjugate Gradient optimization
- Restricted Boltzmann Machine, Deep Belief Network
- Contrastive Divergence, Persistent Contrastive Divergence
- Max/Average Pooling
- Data Augmentation
- Auto-encoders