Lectures related to Highway network

Sequence to Sequence Models: Overview and Applications

Covers sequence to sequence models, their architecture, applications, and the role of attention mechanisms in improving performance.

Ball-and-socket joint pose estimation

Focuses on ball-and-socket joint pose estimation using a magnetic field in an anthropomorphic design with artificial muscles and tendons.

Evaluating Machine Accuracy and Robustness on ImageNet

Explores the evaluation of machine and human accuracy and robustness on ImageNet, highlighting progress, challenges, and the need for improvement.

Long Short-Term Memory Networks

Introduces Long Short-Term Memory (LSTM) networks as a solution to vanishing and exploding gradients in recurrent neural networks.

Deep Learning: Recurrent Neural Networks

Explores Recurrent Neural Networks for behavioral data, covering Deep Knowledge Tracing, LSTM, GRU networks, hyperparameter tuning, and time series prediction tasks.

Machine Translation: Attention Mechanism

Explores the attention mechanism in machine translation, addressing the bottleneck problem and improving NMT performance significantly.

Recurrent Neural Networks: Neural Language Models

Explores fixed-context neural language models, RNNs, vanishing gradients, and sequence labeling in NLP.

Recurrent Neural Networks: LSTMs & GRUs

Explores LSTM and GRU variants in recurrent neural networks, addressing challenges and advantages.

Transformers: Pretraining and Decoding Techniques

Covers advanced transformer concepts, focusing on pretraining and decoding techniques in NLP.

Recurrent Neural Networks: Training and Challenges

Discusses recurrent neural networks, their training challenges, and solutions like LSTMs and GRUs.

Batch Normalization: Why It Works

Explores the aim and process of batch normalization in deep neural networks, emphasizing its importance in stabilizing mean input and solving the vanishing gradient problem.

Synaptic Plasticity: Online Memory Learning

Explores synaptic plasticity, spike-timing models, and online memory learning challenges in computational neuroscience.

Transformers: Revolutionizing Attention Mechanisms in NLP

Covers the development of transformers and their impact on attention mechanisms in NLP.

Quantum State Tomography: Neural Network Approach

Explores a neural network approach to quantum state tomography using RBM, showcasing accurate predictions and potential applications beyond RBMs.

Convolutional Neural Networks: Structure & Regularization

Explores Convolutional Neural Networks, data augmentation, weight decay, and dropout for enhancing model performance.

Deep Learning: Backward Propagation and Vanishing Gradient

Delves into backward propagation in deep learning, addressing the vanishing gradient challenge and the need for effective hidden units.

NFNets: Removing BatchNorm for High-Performance Image Recognition

Explores NFNets as an alternative to BatchNorm in ResNets, achieving high performance on ImageNet.

Deep Learning Techniques: Recurring Networks and LSTM Models

Discusses the implementation and optimization of recurring networks using LSTM models in deep learning.

Part-of-Speech Tagging: Probabilistic Models

Explores Part-of-Speech tagging using probabilistic models like Hidden Markov Models and discusses the resolution of lexical ambiguities.

Convolutional Neural Networks: Semantic Segmentation

Explores Convolutional Neural Networks for semantic segmentation, discussing models for pixel classification, learned decoding, and the importance of skip connections.