Center for Language & Speech Processing(CLSP), JHU Courses

A Stochastic Feedback Model for Image Retrieval

Explore a stochastic feedback model for image retrieval, presented by Donald Geman from Johns Hopkins University's Center for Language & Speech Processing.

• YouTube
• 1 hour 23 minutes
• On-Demand
• Free Video

Deterministic Annealing for Clustering, Classification and Speech Recognition

Explore deterministic annealing for improved clustering and classification, avoiding local optima and optimizing various structures in machine learning applications.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Cognitive Computing - An NLP Renaissance

Explore cognitive computing and NLP advancements, including statistical models for parsing, question-answering, and machine translation. Learn about progress in MT quality and its impact on human translators.

• YouTube
• 58 minutes
• On-Demand
• Free Video

Coupled Excitable Systems: How Cells Migrate

Explore cell migration through excitable systems theory. Discover how spontaneous and directed cell movement can be explained using a comprehensive model based on wave propagation and molecular regulators.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

A Short Introduction to Arabic Natural Language Processing

Explore challenges and solutions in Arabic NLP, including morphological complexity, ambiguity, and dialectal variations. Learn about key technologies and resources for processing Arabic language.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

Texts Come from People - How Demographic Factors Influence NLP

Explore how demographic factors influence language use and NLP systems, combining sociolinguistics and statistical methods to improve performance and fairness in natural language processing.

• YouTube
• 52 minutes
• On-Demand
• Free Video

Bayesian Models for Social Interactions - 2013

Explore Bayesian models for analyzing social interactions, focusing on statistical techniques to understand human behavior and relationships in various contexts.

• YouTube
• 59 minutes
• On-Demand
• Free Video

How Does the Brain Solve Visual Object Recognition - 2012

Explore the brain's solution to visual object recognition, focusing on neuronal activity patterns in the primate ventral visual stream and their sufficiency in explaining human performance.

• YouTube
• 1 hour 26 minutes
• On-Demand
• Free Video

How Important is "Starting Small" in Language Acquisition - 2001

Explore connectionist simulations challenging the "starting small" theory in language acquisition, examining critical period effects and implicit prediction in language learning.

• YouTube
• 1 hour 14 minutes
• On-Demand
• Free Video

Low-Pass Semantics with a Bit of Discourse - November 2013

Explore advances in natural language processing and the challenge of creating systems that understand text, with insights on leveraging distributional regularities for effective analysis.

• YouTube
• 1 hour 13 minutes
• On-Demand
• Free Video

Social Applications of Pre-trained Language Models

Explore social applications of pre-trained language models, focusing on automated approaches to investigate stereotypes, prejudice, and propaganda in text, and examine societal impacts of NLP technology.

• YouTube
• 56 minutes
• On-Demand
• Free Video

Recent Progress in Acoustic Speaker and Language Recognition - October 2013

Explore recent advancements in speaker and language recognition, focusing on GMM subspace methods, pattern classification, and Bayesian approaches for improved performance and domain adaptation.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Learning with Marginalized Corrupted Features

Explore machine learning with marginalized corrupted features, a novel approach to enhance generalization and scalability in finite data scenarios. Discover applications in risk minimization and document representation.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

Neural Networks for Speech Recognition - 2013

Explore the evolution of neural networks in speech recognition, from early experiments to modern hybrid HMM/MLP approaches, with insights from a leading expert in the field.

• YouTube
• 1 hour 13 minutes
• On-Demand
• Free Video

Submodularity and Big Data

Explore submodular functions for big data challenges in document summarization, speech recognition, machine translation, and computer vision. Learn efficient algorithms and optimal results.

• YouTube
• 1 hour 16 minutes
• On-Demand
• Free Video