1. Addressing Overfitting Issues with Deep Learning Model for Video Action Recognition Open Access Author: Muralidhar, Shivran Title: Addressing Overfitting Issues with Deep Learning Model for Video Action Recognition Area of Honors: Computer Engineering Keywords: deep learningmachine learningvideo recognitioncomputer vision File: Download Muralidhar_Shivran_Addressing_Overfitting_Issues_with_Deep_Learning_Model.pdf Thesis Supervisors: Vijaykrishnan Narayanan, Thesis SupervisorVijaykrishnan Narayanan, Thesis Honors AdvisorJohn Morgan Sampson, Faculty Reader
2. A PLAN for Tackling the Locust Crisis in East Africa: Harnessing Spatiotemporal Deep Models for Locust Movement Forecasting Open Access Author: Gluck, Jared Paul Title: A PLAN for Tackling the Locust Crisis in East Africa: Harnessing Spatiotemporal Deep Models for Locust Movement Forecasting Area of Honors: Computer Science Keywords: aiai for social gooddeep learningmachine learninglocusts File: Download Gluck_Jared_thesis.pdf Thesis Supervisors: Amulya Yadav, Thesis SupervisorJesse Louis Barlow, Thesis Honors Advisor
3. Utilizing Deep Learning and Computer Vision to Detect Defects in a 3D Printed Product in a Manufacturing Environment Open Access Author: Farkas, Alyson Title: Utilizing Deep Learning and Computer Vision to Detect Defects in a 3D Printed Product in a Manufacturing Environment Area of Honors: Letters, Arts, and Sciences (Abington) Keywords: transfer learningdeep learning3D printingrobot armmanufacturing defectsblemish detectionMATLABneural networkquality assuranceroboticsengineeringcomputer visionartificial intelligence File: Download Farkas_Alyson_Thesis_.pdf Thesis Supervisors: Robert Louis Avanzato, Thesis SupervisorDave Ruth, Thesis Honors Advisor
4. using physics-informed generative adversarial networks to enhance multiphase fluid flow simulation Open Access Author: Li, Matthew Title: using physics-informed generative adversarial networks to enhance multiphase fluid flow simulation Area of Honors: Computer Science Keywords: machine learningdeep learningcomputational fluid dynamicscfdnovel methodphysics-informed neural network File: Download thesis_matthew_li.pdf Thesis Supervisors: Chris Mc Comb, Thesis SupervisorJesse Louis Barlow, Thesis Honors Advisor
5. spectral study of neural networks with ReLU and hat activation functions Open Access Author: Tan, Qinyang Title: spectral study of neural networks with ReLU and hat activation functions Area of Honors: Mathematics Keywords: mathdeep learningfinite element methodsReLU File: Download thesis.pdf Thesis Supervisors: Qingguo Hong, Thesis SupervisorAnna L Mazzucato, Thesis Honors Advisor
