Energy Based Models and Self-Supervised Learning
Explore energy-based models, latent variables, and self-supervised learning. Dive into EBM training, inference, and comparison with probabilistic models. Discover contrastive methods and applications like K-means and BERT.
CNN Applications, RNN, and Attention
Explore CNN applications in digit recognition, object detection, and semantic segmentation. Dive into RNNs, addressing their challenges with attention mechanisms, GRUs, LSTMs, and Seq2Seq models.
Optimisation
Explore optimization techniques for neural networks, including gradient descent, SGD, momentum, adaptive methods, and normalization layers, with real-world applications in MRI technology.
Convolutional Neural Networks
Explore convolutional neural networks, from basic concepts to modern implementations. Learn about kernels, biological inspirations, CNN evolution, and their advantages in image processing and feature extraction.
Stochastic Gradient Descent and Backpropagation
Explore stochastic gradient descent, backpropagation, and neural network implementation in PyTorch. Learn practical tricks, basic modules, and gradient computation for effective deep learning.
History, Motivation, and Evolution of Deep Learning
Explore the history, motivation, and evolution of deep learning, covering key concepts like gradient descent, backpropagation, CNNs, and feature extraction in neural networks.
Recurrent Neural Nets - RNNs
Explore recurrent neural networks, from basic concepts to advanced LSTM architectures. Learn implementation techniques and training strategies for sequence data processing.
Convolutional Neural Nets - CNNs
Explore locality, stationarity, and compositionality in natural input data using convolutional neural networks. Learn CNN components, parameter sharing, and hands-on implementation.
Recurrent Neural Networks - Training Example
Learn to train Recurrent Neural Networks through a hands-on example, exploring the learning problem, coding implementation, and prototyping process.
CNN Loss
Explore convolutional neural network loss functions, including mean square error, cross-entropy, and negative log likelihood, with practical examples and implementation insights.
CNN Training
Learn to train Convolutional Neural Networks using the optim package, covering objective functions, datasets, training scripts, and gradient optimization techniques.
Model-Based Deep Learning with Applications to Imaging - Yonina Eldar, PhD
Explore model-based deep learning approaches for efficient, interpretable networks in signal and image processing, with applications in imaging, ultrasound, and COVID-19 detection.
Memory Augmented Networks
Learn about memory augmented networks, including architecture, attention mechanisms, and applications in machine translation, with a focus on improving generalization in deep learning models.
Deep Q-Networks
Learn advanced reinforcement learning techniques, focusing on Deep Q-Networks. Explore approximation, optimization, and practical implementations to enhance AI decision-making capabilities.
Normalizing Flows - Priyank Jaini
Explore normalizing flows, density estimation, and autoregressive models. Learn about change of variables, increasing triangular maps, and neural autoregressive flows.
Convolutional Neural Networks
Explore convolutional neural networks, from basic concepts to advanced architectures, including edge detection, pooling, and feature maps for image recognition tasks.
Autoencoders
Explore autoencoders, from basic concepts to advanced applications, covering compression, PCA, deep architectures, sparse representations, and denoising techniques.
CS480-680 Lecture 19 - Attention and Transformer Networks
Explore attention mechanisms, transformer networks, and their applications in machine learning, including multihead attention and normalization techniques.
Deep Neural Networks
Explore deep neural networks, activation functions, and optimization techniques. Learn about gradient vanishing and solutions like rectified linear units.
MIT Introduction to Deep Learning
Comprehensive introduction to deep learning fundamentals, covering perceptrons, neural networks, loss functions, gradient descent, backpropagation, and regularization techniques.
Deep Learning for Scientific Computing - Two Stories on the Gap Between Theory & Practice - Ben Adcock
Explores deep learning in scientific computing, highlighting limitations and recent theoretical advancements in high-dimensional function approximation and inverse problems for imaging, aiming to bridge the gap between theory and practice.