By Meenakshi Khosla explores data-driven modeling in large-scale naturalistic neuroscience, focusing on brain activity representation and computational models.
Explores neural networks' ability to learn features and make linear predictions, emphasizing the importance of data quantity for effective performance.
Explores Convolutional Neural Networks for semantic segmentation, discussing models for pixel classification, learned decoding, and the importance of skip connections.
Covers the basics of Natural Language Processing, from traditional to modern approaches, highlighting the challenges and importance of studying both methods.
Covers wildfire susceptibility mapping using ML-Al robotics and various related topics, including experimental protocols, DFT feature engineering, SimpedCLIP, and Covid-19 detection.
Explores clustering methods for partitioning data into meaningful classes when labeling is unknown, covering K-means, dissimilarity measures, and hierarchical clustering.