Publications
Hallucinations in GPT-2 trained model
Jan 25, 2025Journal Ingénierie des Systèmes d’Information
DOI 10.18280/isi.300104
Issue 30
Volume 1
This paper analysis the phenomenon of "hallucinations" in text generated by GPT-2 when it produces irrelevant or illogical content. This work has quantified the extent of those hallucinations and look into ways of their mitigation. By using two main techniques: cosine similarity and frequency analysis. These techniques calculate coherency and relevance in the text produced by OpenAI GPT-2 at different training levels. Where a study case was implemented to train the model and ask the questions and retrain the model using these replays. The main findings indicate that this model hallucinates much less at the beginning of learning, with the situation significantly improving as training progresses. Extreme learning does not eliminate all such inadequacies, and more over-training led to more hallucinations. The hallucinated items span from smaller deviations to major content-wise deviations. An inspection reveals some patterns and cues that are predictive of increased output unreliability of the model. This research suggests a stricter training program that involve varied data sets to reduce the rate of hallucinations. More importantly, improve the accuracy of the model by reaching superior levels through the embedding of contextual and factual anchoring systems as well as designing algorithms for higher trigger identification. Other recommendations of the paper include post-generation text evaluation and continuous research to enhance the complexity of the models.
A ROS-Gazebo Interface for the Katana Robotic Arm Manipulation
Jun 30, 2021Journal Ukh journal of science and engineering
Publisher Univeristy of Kurdistan Hewler
DOI 10.18280/isi.300104
Issue 8
Volume 5
Nowadays, simulators are being used more and more during the development of robotic systems due to the efficiency of the development and testing processes of such applications. Undoubtedly, these simulators save time, resources and costs,as well as enableease of demonstrations of the system. Specifically, tools like the open source Robotic Operating System (ROS) and Gazebo have gained popularity in building models of robotic systems. ROS is extensively used in robotics due to the pros of hardware abstraction and code reuse. The Gazebo platform is used for visualisation because of its high compatibility with ROS. In this paper, ROS and Gazebo have been integrated to build an interface for the visualisation of the Katana Armmanipulator.
Performance evaluation of harmonics on power quality: case study
Jan 1, 2016Journal The International Journal of Energy and Engineering Sciences
DOI 10.18280/isi.300104
Issue 1
Volume 1
This work is proposed the results of current and voltage measurements in the real low voltage distribution system and explains the effects of Harmonics in the Power System with high accuracy with many factors, the relationship between the load and no load and its effects on electrical equipment are practically analyzed , caused by connecting the resistive load and no loading with conclusion two form frequencies, the system behavior is analyzed using the power quality analyzer device (Fluke-435B). This paper will imitate to these sets and include graphs which should explain the variances between individual power quality disturbances. the analysis of the results with respect to k factor and THD and how these can be analyzed to check more successfully w.r.t IEEE 519 are showed. The elements of the distribution system consist of:1 kVA transformer, load resister, and Adjustable Speed Drivers(ASJ) are modeled