A5061135580- Speech and Audio Processing
- Speech Recognition and Synthesis
- Topic Modeling
- Natural Language Processing Techniques
- Teaching and Learning Programming
- Text Readability and Simplification
- Anaerobic Digestion and Biogas Production
- Handwritten Text Recognition Techniques
- Adversarial Robustness in Machine Learning
- Web Data Mining and Analysis
- Open Education and E-Learning
- Congenital Diaphragmatic Hernia Studies
- Domain Adaptation and Few-Shot Learning
- Hernia repair and management
- Clinical practice guidelines implementation
- Advanced Data Compression Techniques
- Agriculture Sustainability and Environmental Impact
- Pleural and Pulmonary Diseases
- Municipal Solid Waste Management
- Trauma Management and Diagnosis
- ICT in Developing Communities
Stanford University
2023
Université Kofi Annan de Guinée
2023
Julius Nyerere University of Kankan
2023
Ignace Deen Hospital
2023
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and adaptable to wide range downstream tasks. We call these foundation underscore their critically central yet incomplete character. This report provides thorough account opportunities risks models, ranging from capabilities language, vision, robotics, reasoning, human interaction) technical principles(e.g., model architectures, training procedures, data, systems,...
Modern deep learning models often achieve high overall performance, but consistently fail on specific subgroups. Group distributionally robust optimization (group DRO) addresses this problem by minimizing the worst-group loss, it fails when group losses misrepresent performance differences between groups. This is common in domains like speech, where widely used connectionist temporal classification (CTC) loss scales with input length and varies linguistic acoustic properties, leading to...
For many of the 700 million illiterate people around world, speech recognition technology could provide a bridge to valuable information and services. Yet, those most in need this are often underserved by it. In countries, tend speak only low-resource languages, for which datasets necessary development scarce. paper, we investigate effectiveness unsupervised representation learning on noisy radio broadcasting archives, abundant even languages. We make three core contributions. First, release...
Teaching Computer Science (CS) by having students write programs hand on paper has key pedagogical advantages: It allows focused learning and requires careful thinking compared to the use of Integrated Development Environments (IDEs) with intelligent support tools or "just trying things out". The familiar environment pens also lessens cognitive load no prior experience computers, for whom mere basic usage computers can be intimidating. Finally, this teaching approach opens opportunities...
Teaching Computer Science (CS) by having students write programs hand on paper has key pedagogical advantages: It allows focused learning and requires careful thinking compared to the use of Integrated Development Environments (IDEs) with intelligent support tools or "just trying things out". The familiar environment pens also lessens cognitive load no prior experience computers, for whom mere basic usage computers can be intimidating. Finally, this teaching approach opens opportunities...
Introduction : Le but de cette étude était d’étudier les indications et résultats des réinterventions précoces chez opérés l’abdomen dans le service chirurgie générale l’HRK. Méthodologie Il s’agissait d’une prospective d’un an, réalisé Chirurgie l’hôpital Régional Kankan portant sur ré-interventions quel que soit lieu l’intervention. Résultats Durant période, nous avons 1075 patients parmi lesquels 38 cas rélaparotomies, 3,53%. L’âge moyen nos malades 29,68 ans avec extrêmes 7 75 ans,...
Introduction: The aim of this study was to assess the management inguinal hernias in general surgery department Siguiri. Methodology: This a retrospective descriptive conducted over period 2 years (January 1, 2021 - December 31, 2022) Prefectural Hospital Siguiri, Guinea. included all patients admitted and treated for during period. Results: During period, 1248 surgical procedures were performed, which 328 (26.28%) hernias. average age 37.39 years. Males most affected, accounting 91.5%...
For many of the 700 million illiterate people around world, speech recognition technology could provide a bridge to valuable information and services. Yet, those most in need this are often underserved by it. In countries, tend speak only low-resource languages, for which datasets necessary development scarce. paper, we investigate effectiveness unsupervised representation learning on noisy radio broadcasting archives, abundant even languages. We make three core contributions. First, release...
Traumatic rupture of the right diaphragmatic dome with herniation a segment hail into thorax is rare lesion. It often result thoraco-abdominal trauma. can generally lead to early or late cardiopulmonary complications due compression. The objective this clinical case study physiopathological mechanisms, diagnostic and therapeutic modalities complication. diagnosis difficult in front since there are no specific signs. In our case, picture on arrival was that high occlusion an immediate...
Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions people across multiple West African countries, which holds significant cultural and educational value. To address this issue, we present set tools, resources, baseline results aimed towards the development systems Nko other languages that do not currently have sufficiently large parallel text corpora available. (1) Fria$\parallel$el: A novel collaborative curation software incorporates...
Moussa Doumbouya, Baba Mamadi Diané, Solo Farabado Cissé, Djibrila Abdoulaye Sow, Séré Daouda Bangoura, Fodé Moriba Bayo, Ibrahima Sory 2. Conde, Kalo Mory Chris Piech, Christopher Manning. Proceedings of the Eighth Conference on Machine Translation. 2023.