Join us on July 17 for the next ScHARe Think-a-Thon! We’ll explore #AI-ready datasets and computational strategies that can unlock the power of #DataScience for your data analysis goals. During this comprehensive review, NIMHD staff will provide hands-on training on: 💡 How to prepare an AI-ready dataset using gold standard data management principles 💡 How to choose from among major computational strategies, including AI, Machine Learning, and statistics No prior knowledge or training required! ScHARe Think-a-Thons are for researchers, educators, and students from all disciplines, career levels, and data science backgrounds. Register today: bit.ly/TaT-July-2024s. ScHARe Think-a-Thons are sponsored by NIMHD and National Institute of Nursing Research (NINR)
National Institute on Minority Health and Health Disparities (NIMHD)’s Post
More Relevant Posts
-
This looks fascinating (and fun)! "This webinar helps unlock the power of data science computational strategies, demystifying the process of choosing between Artificial Intelligence, Machine Learning, and traditional statistics."
Learn how to choose computational strategies for your #DataAnalysis goals at the next ScHARe Think-a-Thon on January 17! This interactive webinar will demystify the process of choosing computational tools and techniques and prepare you for data science coursework. NIMHD staff will provide hands-on training on: 💡 Understanding the fundamental differences between #ArtificialIntelligence (AI), #MachineLearning (ML), and traditional statistical approaches 💡 Identifying common use cases for each approach 💡 Using ScHARe’s free infographics, templates, and decision trees to empower confident choices between computational strategies All disciplines, career levels, and levels of #DataScience experience are welcome! Register today to attend: bit.ly/think-a-thon-11s. ScHARe Think-a-Thons are sponsored by NIMHD and National Institute of Nursing Research (NINR).
To view or add a comment, sign in
-
#riddleanswer Appreciation goes to everyone who took a moment to engage with our post. Congratulations MILLICENT OMONDI for getting the answer right first. Transfer learning can significantly speed up the training process and enhance model performance on new tasks by leveraging knowledge gained from previous tasks. For instance, consider a deep learning model pre-trained on a large image dataset like #ImageNet to recognize general features such as edges and textures. This pre-trained model can then be fine-tuned for a specific task, such as identifying different types of medical images, with much less data and training time compared to training a model from scratch. This approach not only #accelerates the training but also #improves accuracy by utilizing the features learned from the extensive dataset. Congratulations once again to all those who answered correctly! #machinelearning #datascience #riddles
To view or add a comment, sign in
-
Congratulations to Dhivyabharathi Ramasamy on successfully defending her PhD thesis titled «Towards AI-Assisted Data Science Development. Decoding, Visualising, and Enhancing Human-AI Collaboration for Data Science Workflows in Practice». Her thesis addresses critical challenges in data science development and presents a robust framework for empirically studying data science workflows. She investigates the challenges and potential of AI assistants, such as the GPT-4 model, in performing data science tasks and proposes methods to generate more effective coding recommendations. Additionally, she presents solutions to improve the comprehension of data science code. Through these contributions, her research paves the way for smarter tools to support data scientists using computational notebooks and advances AI-assisted development in the field of data science. We wish Dhivya all the best for the future! #PhD #thesis #DataScience #GenerativeAI #AIAssistants #HCI #uzhifi
To view or add a comment, sign in
-
Heart Disease Prediction Hello everyone! I am delighted to share my 3rd Machine Learning project, which predicts the presence of heart disease using supervised learning algorithms. Methodology: 1. Data Importation: Retrieved and loaded the heart disease dataset. 2. Data Preparation: Conducted thorough cleaning and preprocessing of the data. 3. Feature and Label Separation: Segregated input features (X) from the output labels (Y). 4. Data Splitting: Divided the dataset into training and testing subsets. 5. Normalization: Standardized the data using Standard Scaler for enhanced performance. 6. Model Development: Created predictive models using the KNN algorithm. 7. Performance Evaluation: Assessed model efficacy using a confusion matrix and accuracy score. Tools and Mentorship IDE: Google Colab Mentor: Sabir K, Luminar Technolab #MachineLearning #DataScience #Colab #GoogleColab #ml #ai
To view or add a comment, sign in
-
Social Impact Manager, Consultant and Trainer | Data Science and Impact Assessment | PhD in Distance Education
📚 🎓 "Causal and Trustworthy Machine Learning: Methods and Applications" is the name of the doctoral thesis presented last year by Limor Gultchin at the University of Oxford. This thesis explores how machine learning and causal inference can benefit each other, paving the way for significant advances in both fields. 💡 📚 The thesis addresses the application of machine learning techniques to calculate causal quantities and uses ideas of causal inference to make more accurate and reliable predictions. Additionally, it explores how machine learning can be applied ethically and fairly, focusing on the interpretability and fairness of models. 📈 Among the key themes, the research includes: - Methods for estimating causal effects with partial knowledge of causal graphs. - Analysis of causal effects in complex data, such as images and texts. - Perspectives on explainable and fair machine learning. 🔍It's worth taking a look at: https://lnkd.in/dr_7bixA #machinelearning #research #data #socialimpact, #behavioranalytics #data4good #socialgood #datascientists #algorithms #causality #causalinference #causalml #uplift #datascience #econometrics #CATE #HTE
To view or add a comment, sign in
-
Process Associate @Wipro | Passionate Coder & Problem Solver | 5 🌟 Hacker Rank | CSE Graduate '24 | Passionate Data Analyst | Proficient in Power BI, Excel, SQL, Python
🌟 Exciting News! 🌟 I am thrilled to announce the successful completion of my final year project on "Diabetes Prediction Using Machine Learning"! 🎓🤖 Over the past 1 year, I've delved into the fascinating world of machine learning algorithms to develop a predictive model aimed at early detection of diabetes. This project has been a culmination of my academic journey, combining my passion for healthcare and technology. Key highlights of the project include: 🔍 Data collection and preprocessing to ensure accuracy and reliability. 📊 Implementation of various machine learning techniques such as Random Forest Classifier, Support Vector Machine & many more. 📈 Evaluation of model performance was done using metrics like accuracy. I am immensely grateful to my teachers for their invaluable guidance and support throughout this journey. Their expertise has been instrumental in shaping this project into what it is today. This project has not only sharpened my technical skills but has also deepened my understanding of the critical role that machine learning can play in healthcare. I am excited about the potential impact of this work in improving early diagnosis and management of diabetes. Looking ahead, I am eager to apply these learnings in practical settings and contribute meaningfully to the field of healthcare technology. Thank you to everyone who has supported me along the way. I look forward to sharing more about my project and discussing its implications with you all. 😍 GitHub Link : https://lnkd.in/gnq-sy9M Demo Link: https://lnkd.in/g8ga4Pr8 #MachineLearning #HealthTech #FinalYearProject #DiabetesPrediction #DataScience #AI #ML
To view or add a comment, sign in
-
D.R D.Y Patil institute of engineering management and research | Artificial intelligence and data science |
Excited to share an achievement: I've completed the Machine Learning Specialization in Supervised Learning from Stanford Online and deeplearning.ai! After immersing myself in the rigorous curriculum provided by two renowned institutions, I've gained invaluable insights into the world of supervised learning. Throughout the program, I delved deep into topics such as predictive modeling, classification algorithms, and regression analysis. I extend my heartfelt gratitude to the exceptional instructors at Stanford Online and deeplearning.ai for their guidance and expertise. #machinelearning #stanforduniversity #supervisedlearning #classification #deeplearningai
To view or add a comment, sign in
-
"As a student, of course, this building is especially exciting," said Ph.D. in Data Science Candidate, Navya Annapareddy, during her remarks at the grand opening celebrations of the School of Data Science. "And while it might be ironic for a school to celebrate getting walls, in a field as digital and distributed as ours, this physicality is priceless. Imagine students in classrooms, working on data sets changing in real-time. Imagine their application having immediate value to themselves and society. Imagine academic labs, not working in silos, but directly with industry peers and government. Many of whom are in this room. Imagine the perspectives we can have and host here with Washington D.C as our backyard as a thought leader in data science and a form for communication." You can hear more of Navya's speech by clicking here: https://bit.ly/4ba7ed1 Image by Tom Cogill #DataScience #UVA #UVADataScience #AI #ArtificialIntelligence
To view or add a comment, sign in
-
Data Scientist | MSc. Data Science @ Newcastle University | Specialist in Cloud and Machine Learning Technologies
I'm thrilled to announce that I've started my dissertation project at the National Innovation Centre for Data under the guidance of Peter Michalák and Jacek Cała. Through my research, I aim to explore how model compression techniques can enhance the efficiency and scalability of federated learning systems. Federated learning is a revolutionary approach where machine learning models are trained across decentralised devices while preserving data privacy. Unlike traditional centralised methods, federated learning allows for collaborative model training without the need to share raw data. This innovative technique holds immense potential in industries where data privacy is paramount, such as healthcare and finance. Excited to delve deep into this cutting-edge field and contribute to advancements in collaborative machine learning! #FederatedLearning #MachineLearning #DataScience #Research #ModelCompression Flower Labs #Finance #HealthCare #EdgeAI #ComputerVision #Communication #ImageRecognition #PyTorch #Pruning #Quantization #EdgeComputing #Collaboration
To view or add a comment, sign in
52,571 followers
More from this author
-
The First Americans in Minority Health and Health Disparities Research: Dr. Teresa Brockie
National Institute on Minority Health and Health Disparities (NIMHD) 1y -
Environmental Risk Factors for Prostate Cancer in Overburdened, Understudied Populations
National Institute on Minority Health and Health Disparities (NIMHD) 2y -
Striving Towards Health Equity: Understanding the Impact of Discrimination on LGBTQ+ Communities
National Institute on Minority Health and Health Disparities (NIMHD) 2y