Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has made it increasingly popular thanks to its low cost and the availability of libraries that support merging on consumer GPUs. Recent work shows that pairing merging with evolutionary algorithms can boost performance, but no framework currently supports flexible experimentation with such strategies in language models. We introduce Mergenetic, an open-source library for evolutionary model merging. Mergenetic enables easy composition of merging methods and evolutionary algorithms while incorporating lightweight fitness estimators to reduce evaluation costs. We describe its design and demonstrate that Mergenetic produces competitive results across tasks and languages using modest hardware.

Ensuring the security and reliability of machine learning frameworks is crucial for building trustworthy AI-based systems. Fuzzing, a popular technique in secure software development lifecycle (SSDLC), can be used to develop secure and robust software. Popular machine learning frameworks such as PyTorch and TensorFlow are complex and written in multiple programming languages including C/C++ and Python. We propose a dynamic analysis pipeline for Python projects using the Sydr-Fuzz toolset. Our pipeline includes fuzzing, corpus minimization, crash triaging, and coverage collection. Crash triaging and severity estimation are important steps to ensure that the most critical vulnerabilities are addressed promptly. Furthermore, the proposed pipeline is integrated in GitLab CI. To identify the most vulnerable parts of the machine learning frameworks, we analyze their potential attack surfaces and develop fuzz targets for PyTorch, TensorFlow, and related projects such as h5py. Applying our dynamic analysis pipeline to these targets, we were able to discover 3 new bugs and propose fixes for them.

It attempts to provide most of the functionality provided by the official Python API, while at the same type being strongly-typed and adding some new features. It is a work in progress and a project I started working on for my personal research purposes. Much of the API should be relatively stable by now, but things are still likely to change. Please refer to the main website for documentation and tutorials. For example, the following code shows how simple it is to train a multi-layer perceptron for MNIST using TensorFlow for Scala.

What is a Deep Learning Framework? A deep learning framework is a software package used by researchers and data scientists to design and train deep learning models. The idea with these frameworks is to allow people to train their models without digging into the algorithms underlying deep learning, neural networks, and machine learning. These frameworks offer building blocks for designing, training and validating models through a high level programming interface. Widely used deep learning frameworks such as PyTorch, TensorFlow, MXNet, and others can also use GPU-accelerated libraries such as cuDNN and NCCL to deliver high-performance multi-GPU accelerated training.

A deep learning framework is a software package used by researchers and data scientists to design and train deep learning models. The idea with these frameworks is to allow people to train their models without digging into the algorithms underlying deep learning, neural networks, and machine learning. These frameworks offer building blocks for designing, training, and validating models through a high-level programming interface. Widely used deep learning frameworks such as PyTorch, TensorFlow, MXNet, and others can also use GPU-accelerated libraries such as cuDNN and NCCL to deliver high-performance multi-GPU accelerated training. An open-source software library created by Google, TensorFlow is a popular tool for machine learning, especially for training deep neural networks.

Artificial Intelligence (AI) has made significant progress in the past 5 years and is playing a more and more important role in power system analysis and control. It is foreseeable that the future power system transient stability simulations will be deeply integrated with AI. However, the existing power system dynamic simulation tools are not AI-friendly enough. In this paper, a general design of an AI-oriented power system transient stability simulator is proposed. It is a parallel simulator with a flexible application programming interface so that the simulator has rapid simulation speed, neural network supportability, and network topology accessibility. A prototype of this design is implemented and made public based on our previously realized simulator. Tests of this AI-oriented simulator are carried out under multiple scenarios, which proves that the design and implementation of the simulator are reasonable, AI-friendly, and highly efficient.

Python can exponentially increase your brain's power by analyzing large amounts of data, but getting started with coding can be just as chaotic as joining any other community in everyday life. There are various versions of the language, various modules for accomplishing the same goal, various habits for testing and debugging code, various software programs that can be used as a coding interface, and so on. There are rituals in an everyday culture that provide structure to the chaotic environment we live in. We greet our neighbors, attend school to earn a diploma, and brush our hair in the morning. These activities can be thought of as rituals that provide structure to our interactions with others.

One of the common problems with learning image processing is the high cost of software. In this course, I entirely use open source software including the Google Earth Engine Python API and Colab. All sample data and script will be provided to you as an added bonus throughout the course. Jump in right now and enroll.

Description Do you want to access satellite sensors using Earth Engine Python API and Google Colab? Do you want to learn the spatial data science on the cloud? Do you want to become a geospatial data scientist? I will provide you with hands-on training with example data, sample scripts, and real-world applications. By taking this course, you be able to install Anaconda and Jupyter Notebook.

After developing and selling a Python API, I now want to expand the idea with a machine learning solution. So I decided to quickly write a COVID-19 prediction algorithm, deploy it, and make it sellable. If you want to see how I did it, check out the post for a step by step tutorial. In this article, I take the ideas from my previous article "How to sell a Python API from start to end" further and build a machine learning application. If the steps described here are too rough consider reading my previous article first.