Name: Arno Candel
Type: User
Company: http://h2o.ai
Bio: CTO at H2O.ai,
ML, AI, GenAI, Deep Learning, Data Science, H2O-3, H2O Driverless AI, h2oGPTe. Kaggle Master, PhD Physics ETH, Stanford Linear Accelerator.
Twitter: arnocandel
Location: Los Gatos, CA
Blog: https://www.linkedin.com/in/candel
Arno Candel's Projects
Instruct-tune LLaMA on consumer hardware
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Ethereum miner with CUDA and stratum support
GPU-accelerated LIBSVM is a modification of the original LIBSVM that exploits the CUDA framework to significantly reduce processing time while producing identical results. The functionality and interface of LIBSVM remains the same. The modifications were done in the kernel computation, that is now performed using the GPU.
A CUDA implementation of performing Robust PCA for foreground-background separation, using ADMM for optimization.
Implemented the Kalman Filter Algorithms on GPU using CUDA programming language. Analysed the run-time performance gain obtained by parallel computation of the various stages of the algorithm.Speed up of 1000x is observed for large input sets.
CUDA Data Parallel Primitives Library
My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot
Feather: fast, interoperable binary data frame storage for Python, R, and more powered by Apache Arrow
Gradient boosted models
Code and documentation for the winning sollution to the Grasp-and-Lift EEG Detection challenge
Codes for Kaggle Competitions
2nd place solution for Allstate Claims Severity competition at Kaggle
3rd place solution for the second kaggle national datascience bowl
Kaggle datascience bowl 2017
A CUDA implementation of the k-means clustering algorithm
kmeans
LightGBM is a fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
Tensorflow implementation of the paper "A Neural Algorithm of Artistic Style"
Parenting for Geeks
Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations
Python interface for POGS
The 3rd place solution for Santander Customer Satisfaction competition
Model extraction attacks on Machine-Learning-as-a-Service platforms.
Computation using data flow graphs for scalable machine learning
TensorFlow tutorials and code examples for beginners
Thrust is a parallel algorithms library which resembles the C++ Standard Template Library (STL).