Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Home

Lecture

Pre-Training: BiLSTM and Transformer

About
Privacy
Disclaimer

Graph Chatbot

Related lectures (32)

Neural Networks for NLP Log in to Mediaspace to watch this video

Covers modern Neural Network approaches to NLP, focusing on word embeddings, Neural Networks for NLP tasks, and future Transfer Learning techniques.

Natural Language Processing: Understanding Transformers and Tokenization Log in to Mediaspace to watch this video

Provides an overview of Natural Language Processing, focusing on transformers, tokenization, and self-attention mechanisms for effective language analysis and synthesis.

Deep Learning for NLP Log in to Mediaspace to watch this video

Delves into Deep Learning for Natural Language Processing, exploring Neural Word Embeddings, Recurrent Neural Networks, and Attentive Neural Modeling with Transformers.

BERT: Pretraining and Applications Log in to Mediaspace to watch this video

Delves into BERT pretraining for transformers, discussing its applications in NLP tasks.

Model Analysis Log in to Mediaspace to watch this video

Explores neural model analysis in NLP, covering evaluation, probing, and ablation studies to understand model behavior and interpretability.

Long Short-Term Memory Networks Log in to Mediaspace to watch this video

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

Foundations of Deep Learning: Transformer Architecture Overview Log in to Mediaspace to watch this video

Covers the foundational concepts of deep learning and the Transformer architecture, focusing on neural networks, attention mechanisms, and their applications in sequence modeling tasks.

Deep Generative Models: Part 2 Log in to Mediaspace to watch this video

Explores deep generative models, including mixtures of multinomials, PCA, deep autoencoders, convolutional autoencoders, and GANs.

Modern NLP and Ethics in NLP Log in to Mediaspace to watch this video

Delves into advancements and challenges in NLP, along with ethical considerations and potential harms.

Probabilistic Information Retrieval Log in to Mediaspace to watch this video

Covers probabilistic information retrieval, query likelihood models, language modeling, and relevance feedback algorithms.

Data-driven Reinforcement Learning Log in to Mediaspace to watch this video

Discusses challenges in AI systems, supervised learning limitations, and the necessity of data-driven methods in reinforcement learning.

Optical Computing: All-Analog Photoelectronic Chip for Vision Tasks Log in to Mediaspace to watch this video

Presents an all-analog photoelectronic chip for high-speed vision tasks, addressing challenges in classical computation and proposing a hybrid optical-electrical framework.

Page 2 of 2