SEP-406 Derin Öğrenme ve Uygulamaları

Ders Başlıkları

• Deep Learning’e Giriş
• Neural Networks ve Backpropagation
• Embeddings ve Tavsiye Sistemleri
• Görüntü Sınıflandırma için Convolutional Neural Networks
• Obje Tespiti için Deep Learning ve Resim Segmentasyonu
• Recurrent Neural Networks ve NLP
• Sequence to sequence, attention ve memory
• Expressivity, Optimization and Generalization
• Imbalanced classification ve Metric Learning
• Unsupervised Deep Learning ve Generative models

Lab Başlıkları

• Lab 1: Deep Learning’e giriş
  • Demo: Object Detection with pretrained RetinaNet with Keras
  • Keras ile MLP giriş
• Lab 2: Neural Networks and Backpropagation
  • Numpy kullanarak Neural Networks de Backpropagation
  • Bonus: TensorFlow kullanarak Backpropagation
• Lab 3: Embeddings and Recommender Systems
  • Keras ile Embeddings
  • Explicit Feedback ile Neural Recommender Systems
  • Implicit Feedback ve Triplet Loss ile Neural Recommender Systems
• Lab 4: Resim Sınıflandırma için Convolutional Neural Networks
  • Convolutions
  • Keras ile Pretrained ConvNets
  • Fine Tuning a pretrained ConvNet with Keras (GPU required)
  • Bonus: Convolution and ConvNets with TensorFlow
• Lab 5: Deep Learning for Object Dection and Image Segmentation
  • Fully Convolutional Neural Networks
  • ConvNets for Classification and Localization
• Lab 6: Text Classification, Word Embeddings and Language Models
  • Text Classification and Word Vectors
  • Character Level Language Model (GPU required)
  • Transformers (BERT fine-tuning): Joint Intent Classification and Slot Filling
• Lab 7: Sequence to Sequence for Machine Translation
  • Translation of Numeric Phrases with Seq2Seq
• Lab 8: Intro to PyTorch
  • Pytorch Introduction to Autograd
  • Pytorch classification of Fashion MNIST
  • Stochastic Optimization Landscape in Pytorch
• Lab 9: Siamese Networks and Triplet loss
  • Face verification using Siamese Nets
  • Face verification using Triplet loss
• Lab 10: Variational Auto Encoder
  • VAE on Fashion MNIST

Kaynak

Github üzerinde paylaşılan https://github.com/m2dsupsdlclass/lectures-labs reposu ders kapsamında kullanılmıştır.