Certified Robustness to Programmable Transformations in LSTMs

Deep neural networks for natural language processing are fragile in the face of adversarial examples---small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We present an approach to certifying the robustness of LSTMs (and extensions of LSTMs) and training models that can be efficiently certified. Our approach can certify robustness to intractably large perturbation spaces defined programmatically in a language of string transformations. Our evaluation shows that (1) our approach can train models that are more robust to combinations of string transformations than those produced using existing techniques; (2) our approach can show high certification accuracy of the resulting models.

APIRecX: Cross-Library API Recommendation via Pre-Trained Language Model

For programmers, learning the usage of APIs (Application Programming Interfaces) of a software library is important yet difficult. API recommendation tools can help developers use APIs by recommending which APIs to be used next given the APIs that have been written. Traditionally, language models such as N-gram are applied to API recommendation. However, because the software libraries keep changing and new libraries keep emerging, new APIs are common. These new APIs can be seen as OOV (out of vocabulary) words and cannot be handled well by existing API recommendation approaches due to the lack of training data. In this paper, we propose APIRecX, the first cross-library API recommendation approach, which uses BPE to split each API call in each API sequence and pre-trains a GPT based language model. It then recommends APIs by fine-tuning the pre-trained model. APIRecX can migrate the knowledge of existing libraries to a new library, and can recommend APIs that are previously regarded as OOV. We evaluate APIRecX on six libraries and the results confirm its effectiveness by comparing with two typical API recommendation approaches.

ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models

Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of text and graph leveraging Reinforcement Learning to improve performance. Graph linearization enables us to re-frame both tasks as a sequence to sequence generation problem regardless of the generative direction, which in turn allows the use of Reinforcement Learning for sequence training where the model itself is employed as its own critic leading to Self-Critical Sequence Training (SCST). We present an extensive investigation demonstrating that the use of RL via SCST benefits graph and text generation on WebNLG+ 2020 and TekGen datasets. Our system provides state-of-the-art results on WebNLG+ 2020 by significantly improving upon published results from the WebNLG 2020+ Challenge for both text-to-graph and graph-to-text generation tasks. More details at https://github.com/IBM/regen.

Creating an OpenCV Application Raspberry Pi-Based Beowulf Cluster

This project is about an Arabic guide for building a supercomputer (cluster) based on raspberry pi nodes with a brief of the problems and the solutions needed, with an OpenCV application about counting stars in a Nasa Image

برمجة التطبيقات الشبكية

الفصل الأول : تعددية النياسب الفصل الثاني : برمجة التطبيقات الشبكية زبون-مخدم الفصل الثالث : خدمات الويب

Developing 3D Online Game and Interactive Virtual Environment Control System

Developing 3D Online Game and Interactive Virtual Environment Control System with unity game engine this project is for graduation project in damascus university

Optimization Of Earthmoving Problem With Multiple Soil Types Using Linear Programing

Earthmoving is the process of moving and processing soil from one location to another to alter an existing land surface into a desired configuration. Highways, dams, and airports are typical examples of heavy earthmoving projects. Over the years, construction managers have devised ways to determine the quantities of material to be moved from one place to another. Various types of soil (soft earth, sand, hard clay, …, etc.) create different level of difficulty of the problem. Earthmoving problem has traditionally been solved using mass diagram method or variety of operational research techniques. However, existing models do not present realistic solution for the problem. Multiple soil types are usually found in cut sections and specific types of soil are required in fill sections. Some soil types in cut sections are not suitable to be used in fill sections and must be disposed of. In this paper a new mathematical programming model is developed to find-out the optimum allocation of earthmoving works. In developing the proposed model, different soil types are considered as well as variation of unit cost with earth quantities moved. Suggested borrow pits and/or disposal sites are introduced to minimize the overall earthmoving cost. The proposed model is entirely formulated using the programming capabilities of VB6 while LINDO is used to solve the formulated model to get the optimum solution. An example project is presented to show how the developed model can be implemented.