Concept

Object-modeling language

Related lectures (31)

Explores the significance of System Modeling Languages like OPM, SysML, and Modelica in modern Systems Engineering.

Covers Probabilistic Information Retrieval, including Query Likelihood Model, Language Modeling, and smoothing techniques for non-occurring terms.

Probabilistic Information Retrieval

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

Probabilistic Retrieval Models

Covers probabilistic retrieval models, evaluation metrics, query likelihood, user relevance feedback, and query expansion.

Pretraining: Transformers & Models

Explores pretraining models like BERT, T5, and GPT, discussing their training objectives and applications in natural language processing.

An Introduction to Systems Engineering: Requirements, Architecture, and Concept Generation

Covers the 'V-Model' of Systems Engineering, emphasizing good requirements, system architecture, concept generation, and concept selection.

Probabilistic Retrieval: Practical Relevance Feedback

Explores practical relevance feedback in probabilistic retrieval and query optimization.

Language Modelling and Recurrent Neural Networks

Explores language modelling, RNNs, n-gram models, LSTMs, and bidirectional RNNs.

Prompting and Alignment

Explores prompting, alignment, and the capabilities of large language models for natural language processing tasks.

Probabilistic Retrieval

Covers Probabilistic Information Retrieval, modeling relevance as a probability, query expansion, and automatic thesaurus generation.

Biological structure and function emerge from unsupervised learning

Delves into how biological structure and function are decoded through unsupervised learning of protein sequences.

Optimal Decision Making with CVXPY

Introduces CVXPY for optimal decision making through atomic functions and operators.

Integrative Benchmarking: Advancing System Models of Human Intelligence

Explores advancing system models of human intelligence through integrative benchmarking and the importance of Brain-Score for fair model comparisons.

Modern NLP and Ethics in NLP

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

Pre-Training: BiLSTM and Transformer

Delves into pre-training BiLSTM and Transformer models for NLP tasks, showcasing their effectiveness and applications.

State Space Models: Expressivity and Transformers

Covers state space models and their expressivity compared to transformers, focusing on attention mechanisms and computational efficiency.

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.

Ethical Considerations in Natural Language Processing

Explores ethical challenges in NLP systems, including biases, toxicity, privacy, and disinformation.

Model Interpretation and Compilation

Explores model interpretation, compilation via partial evaluation, function calls, and the transition to partial evaluation, emphasizing the importance of model interpreters in supporting modeling languages.

BERT: Pretraining and Applications

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