Natural language processing (NLP) is one of the most transformative technologies for modern businesses and enterprises. This course will focus on practical applications and considerations of applying deep learning for NLP in industrial or enterprise settings. We will have a practical focus, targeting algorithms, frameworks, and solutions which are able to be deployed in industry today. We will cover the different components that go into end-to-end deep learning systems, including word vector representations (word2vec, GloVe), window-based models, recurrent neural networks (long-short-term-memory (LSTM), gated recurrent units (GRU), etc.), and convolutional neural networks. We will cover classification, named entity recognition, entailment, and other applications, with a focus on models and engineering tricks that allow these algorithms to be pushed to practical use cases in minimum time.
We will be using the Keras library to implement models, and thus, some experience with both Python and Machine Learning is beneficial. Prior exposure to Keras / TensorFlow or any other deep learning library will be helpful, though is not required. A rough understanding of REST/RPC will be useful for some of the practical components, though is not necessary.
- Word Vectors
- Windowed models
- LSTM / GRU / Recurrent Neural Networks
- Convolutional Neural Networks
- Classification / Tagging
- Language Models
- Named Entity Recognition
- Building practical models in Keras
- Inference-time engineering considerations
- Designing serving layers
To view other workshop descriptions, or to get general information about the ICME Summer Workshop Series, click here.
ICME Summer Workshops are open to participants 18 years and older. If you are under the age of 18 and would like to participate, please contact firstname.lastname@example.org.
Questions: please contact the ICME at email@example.com .