Talks

  • Lectures

     

     

    • Multi-Modality and Generative Models – Surveying SOTA Multi-Modal Generative Models (DALL-E 2, Imagen and more), alongside several recent works for expediting generative-model inference (Deep Learning Course 236781).

     

     

     

     

    Tutorials (English)

    • CNNs– Convolutional Layers, Convolutional Neural Networks, Residual Connection
    • Optimization – Key concepts in numerical optimization of neural networks with Pytorch.
    • Object Detection – Fundamental Performance Metrics and Deep-Learning Solutions for Object Detection.
    • Sequence Models – Neural models for sequential data – RNNs, LSTMs, GRUs.
    • Attention – Key concepts in attention for sequence processing.
    • Transformers – Transformer Models, Positional Encoding, Multiheaded Attention.
    • GANs – Intro to generative modeling, Generative Adversarial Neural networks.

    Tutorials (Hebrew)

    • ML Fundamentals – Definition and key concepts of learning problems, Perceptron model, logistic regression.
    • MLPs – Intro to Multilayer-Perceptron models.
    • CNNs– Convolutional Layers, Convolutional Neural Networks, Residual Connection
    • AutoDiff – Pytorch’s mechansim for automatic differentiation.
    • Object Detection – Fundamental Performance Metrics and Deep-Learning Solutions for Object Detection.
    • Sequence Models – Neural models for sequential data – RNNs, LSTMs, GRUs.
    • Attention – Key concepts in attention for sequence processing.
    • Transformers – Transformer Models, Positional Encoding, Multiheaded Attention.
    • GANs – Intro to generative modeling, Generative Adversarial Neural networks.
    • VAEs – Generative modeling with Variational Autoencoders.
    • DDPMs – Intro to generative modeling with diffusion models, DDPM models.
    • Multi Modality – Basic notions in multi-modal deep learning, CLIP.