Salta al contenido principal
Panel lateral
Enlaces de interés
FING
Bedelia
SGAE
OpenFing
Noticias
Redes sociales
Orientacion y consulta
Convivencia
Cursos
Institutos
Tecnólogos
Posgrados
Extensión
Institucional
Más
Buscar
Cerrar
Buscar
Selector de búsqueda de entrada
En este momento está usando el acceso para invitados
Acceder
Página Principal
Expandir todo
Colapsar todo
Abrir índice del curso
Institutos
Ingeniería Eléctrica
DLvis
DETR demo
DETR demo
Perfilado de sección
General
Semana 1 - Clase 1
Semana 2 - Clases 2 y 3
Semana 3 - Clases 3 (cont.) y 4
Semana 4 - Clases 5 y 6
Semana 5 - Clase 7
Semana 5 - Clases 8 y 9
Semana 6 - Clases 10, 11 y 12
Semana 7 - Clases 13 y 14
Semana 8 - Clases 14 (cont.) y 15
Semana 9 - Clases 16 y 17
Semana 10 - Clases 18 y 19
Semana 11 - Control 3 y Clase 20
Ediciones anteriores
DETR demo
Requisitos de finalización
Marcar como hecha
Haga clic en el enlace
DETR demo
para abrir el recurso.
◄ End-to-End Object Detection with Transformers (Carion et al., ETTC 2020)
Ir a...
Ir a...
Formulario de inscripción Aprendizaje Profundo para Visión Artificial 2024
Formulario de evaluación Aprendizaje Profundo para Visión Artificial 2024
Novedades 2024
Consultas 2024
Escolaridad y Carta Motivacional 2024
Entregable 1 2024
Entregable 2 2024
Entregable 3 2024
Evaluación del Obligatorio 1 - 2024
Evaluación del Obligatorio 2 - 2024
Evaluación del Obligatorio 3 - 2024
Desarrollo local
Clase 1 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 1)
"Learning deep architectures for AI". Bengio, Y., Foundations and trends in Machine Learning, 2009.
Deep Learning, LeCun, Bengio, Hinton. Nature 2015
Clase 2 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 2, 3 y 5)
Notas Clasificación de imágenes (Stanford cs231n)
K-Nearest Neighbors Demo (Stanford cs231n)
"The Elements of Statistical Learning". Friedman, Hastie, Tibshirani, R., 2001. New York: Springer (Capítulo 1 y 2)
Probability Cheatsheet
Clase 3 - Slides
Notas Clasificación Lineal (Stanford cs231n)
Demo interactiva - Clasificación Lineal (Stanford cs231n)
Cálculo de derivadas de vectores, matrices, tensores (por E. Learned-Miller)
Clase 4 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 6)
Notas Redes Neuronales 1 (cs231n Stanford)
ConvNetsJS Demo
GF Montufar, R Pascanu, K Cho, Y Bengio, "On the number of linear regions of deep neural networks." NIPS, 2014
Visualizing the Loss Landscape of Neural Nets
Exploring Randomly Wired Neural Networks for Image Recognition
Clase 5 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 6)
Notas Backpropagation (cs231n Stanford)
Backpropagation for a Linear Layer (Justin Johnson)
Clase 6 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 9)
Notas Redes Neuronales Convolucionales - CNNs (cs231n Stanford)
Image Kernels
ConvNetJS CIFAR-10 demo
Clase 7 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 7)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R., "Dropout: a simple way to prevent neural networks from overfitting." JMLR, 2014
Wan, Zeiler, Zhang, LeCun, Fergus - Regularization of Neural Networks using DropConnect - ICML 2013
Keskar et al. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima, ICLR 2017
"Improved Regularization of Convolutional Neural Networks with Cutout", DeVries & Taylor, Arxiv 2017
Huang, G., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J.E. and Weinberger, K.Q., “Snapshot ensembles: Train 1, get M for free.” ICLR 2017
Clase 8 - Slides
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 8)
"Large-scale machine learning with stochastic gradient descent." Bottou, L., 2010.
Gradient Descent Converges to Minimizers, J. D. Lee, M, Simchowitz, M. Jordan, B. Recht, 2016
Visualizing the Loss Landscape of neural nets, H. Li, Z. Xu , G. Taylor, C. Studer , T. Goldstein
Escaping Saddles with Stochastic Gradients, H. Daneshmand, J. Kohler, A. Lucchi, T. Hofmann, 2018
Clase 9 - Slides
Notas Redes Neuronales 2 (cs231n Stanford)
"Deep learning" Goodfellow, Bengio, Courville, 2016. MIT press. (Capítulo 11)
Ioffe, S. and Szegedy, C., Batch normalization: Accelerating deep network training by reducing internal covariate shift. ICML 2015
Yuxin Wu, Kaiming He - Group Normalization
Santurkar et al., How Does Batch Normalization Help Optimization?
A Recipe for Training Neural Networks (A. Karpathy)
Clase 10 - Slides
Clase 11 - Slides
Canziani, A., Paszke, A. and Culurciello, "An analysis of deep neural network models for practical applications." arXiv preprint arXiv, 2017
Clase 12 - Slides
Clase 12- Video
Girshick, R., Donahue, J., Darrell, T. and Malik, J.,"Rich feature hierarchies for accurate object detection and semantic segmentation". CVPR 2014
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick "Mask R-CNN" ICCV 2017
Ren, S., He, K., Girshick, R. and Sun, J., "Faster R-CNN: Towards real-time object detection with region proposal networks." NIPS 2015
Girshick, R., "Fast R-CNN." ICCV 2015
UCA DL Summer School - Object Detection Lab Session
Clase 13 - Slides
Clase 14 - Slides
Khipu 2019 Practical - Recurrent Neural Networks
Clase 15 - Slides
Khipu Practical - The Transformer for Natural Language Processing
End-to-End Object Detection with Transformers (Carion et al., ETTC 2020)
Clase 16 - Slides
Auto-Encoding Variational Bayes (Kingma and Welling 2014)
Tutorial on Variational Autoencoders (Carl Doersch)
Van den Oord et al., Pixel Recurrent Neural Networks, ICML 2016
Van den Oord et al., Conditional Image Generation with PixelCNN Decoders, NeurIPS 2016
Kingma y Dhariwal, Glow: Generative Flow with Invertible 1×1 Convolutions, NeurIPS 2018
Clase 17 - Slides
Generative Adversarial Nets (Goodfellow et al, 2014, NIPS)
Generative Adversarial Networks, NIPS 2016 Tutorial (Ian Goodfellow)
Wasserstein GAN (M. Arjovsky)
The GAN Zoo (github)
Metz et al. "Unrolled generative adversarial networks". ICLR 2017
Radford et al. “Unsupervised representation learning with deep convolutional generative adversarial networks.” ICLR 2016
Zhu et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks". ICCV 2017
Karras et al, “Progressive Growing of GANs for Improved Quality, Stability, and Variation”. ICLR 2018
Clase 18 - Slides
Khipu 2023 practical "Deep generative models"
Texture Synthesis Using Convolutional Neural Networks - Gatys et al. - NeurIPS 2015
Image Style Transfer Using Convolutional Neural Networks - Gatys et al. - CVPR 2016
Weight Uncertainty in Neural Networks, Blundell et al. ICML 2015
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles - Lakshminarayanan et al. - NeurIPS 2017
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning - Gal & Ghahramani - ICML 2016
Clase 20 - Slides
Clases 2020 (YouTube)
Clase 16 - Slides ►
