Introduction to Deep learning and NLPs for AI applications (3 days)
by Walid SemaanLanguages: English
Price (from): €1,500 / day
About the trainer:
Walid Semaan is the founder and president of Matrix TRC "Data Science and AI Academy (partners with the SAS Data Science program). He graduated in engineering from Ecole Supérieure d’Ingénieurs à Beyrouth and holds a degree in finance and marketing from the Ecole Supérieure de Commerce de Paris (ESCP) and an MBA from the University Paris-Dauphine-Sorbonne in Paris. He is the creator and architect of the automated analytical artificial intelligence behind “Triple One Analytics,“ winner of the Best Innovative ICT Project at the 2011 Arab Golden Chip Award. Walid is the trainer of all the workshops he wrote, related to research methodologies, data visualization, data analytics, machine and deep learning, quality control, forecasting, epidemiology and big data ecosystem, as well as mostly used proprietary and open-source data analytical tools. Walid joined lately Fleming Events - Europe as an expert trainer in Data Science and is an expert certified trainer in the Middle East for SAS, PWC Academy, MEIRC-PLUS Training, Abu Dhabi Business School, Formatech and Obeikan Digital College. In parallel, he holds thousands of hours teaching master programs at Saint Joseph University, assisting Ph.D. students in their advanced analytics programs, and training local and international companies, to name few from dozens: Central Bank of Lebanon (Lebanon), PWC (Dubai), Vlerick Business School (Belgium), SCAD (Abu Dhabi), OXY Petroleum (Oman), IPSOS (Lebanon), Obeikan Group (KSA), Dallah Hospital (KSA), Smart Dubai (Dubai), DarkMatter (Dubai), Indevco Industries (Lebanon and Egypt) and Algorithm Pharma (Lebanon).
Please login to send a message
Introduction to Deep learning and NLPs for AI applications (3 days) by Walid Semaan
About the training
OVERVIEW
Many factors contributed to the rise of AI and launched the 4th technological revolution. However, one main invention accelerated the process: transforming an image into information. This led the way to transform videos, texts and audios into information. The results? Cars without drivers, bots, and automation of almost at the level of human ability. This session will highlight algorithms behind this breakthrough in technology and make AI a reality.
On the other hand, another important factor boosted that revolution: decoding the secret for analyzing text with Natural Language Processing tools and algorithms. By allowing to understand instantly text from books and the web, to classify it and even to generate text, the AI revolution got onto its feet for a long and extraordinary journey.
OBJECTIVES
By the end of this workshop, you will be able to:
- Apprehend fully the science behind the Artificial Neural Networks (ANN)
- Understand the flow of information throughout the neurons
- Go through the complete process of image recognition with Convolutional Neural Networks (CNN)
- Comprehend how models learn from the input images
- Comprehend the link between ANN and CNN.
- Explore the logic behind Natural Language Processing
- Understand how NLPs analyze, classify and generate text
CONTENT
Artificial Neural Networks
- Neurons
- Hidden layers
- Perceptron
- Synapsis
- Weights
- Scores
- Activation functions: Sigmoid, TanH, ReLU
- Classification with the SoftMax rule
- Google Neural Network live simulator
Convolutional Neural Networks
- AI revolution with image recognition and captioning
- Convolution layers: Strides / Features / Filters
- ConvNet / Pads
- Pooling and Fully connected layers
Recurrent Neural Networks
- The four types of RNNs
- Flow of data
- Short-term memory
- Vanishing and exploding gradient
Long- and Short-Term Memory
- Cell state
- Forget phase
- Update phase
- Convey phase
Natural Language Processing
- Fields of application
- Tokenization
- Stemming
- Lemmatization
- POS tags
- Named Entity Recognition
- Sentiment Analysis
- Topic Modeling
- Text generation
Main benefits
- #Wide collection of the biggest experts
- #Filters for all kinds of needs
- #User friendly platform
- #Fast and cheap
- #Highest level of proficiency