{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/fdee74e15f484ef88d59b6a2a401c8be\" frameborder=\"0\" width=\"1680\" height=\"1260\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1260,"width":1680,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1260,"thumbnail_width":1680,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/fdee74e15f484ef88d59b6a2a401c8be-6b810008f6d02559.gif","duration":310.753,"title":"8-Exploring Linear Algebra in Deep Learning","description":"In this video, I explore the fundamental concepts of linear algebra as they relate to deep learning. We cover essential data structures such as scalars, vectors, matrices, and tensors, and discuss key operations like vector addition, dot products, and matrix multiplication, which are crucial for neural networks. I emphasize the importance of eigenvalues and eigenvectors in understanding transformations and stability, as well as the role of norms in regularization. I encourage you to review these concepts and think about how they apply to your work in deep learning. Thank you for watching!"}