Deep Learning and AI with Python – London - 2-Day Training Course

Description:

1. Course description.

The “Deep Learning with Python” training course is focused on practical implementations of artificial neural networks and deep learning methods using Python programming language with state-of-the-art Python libraries used in AI and predictive analytics e.g. scikit-learn, h2o, keras, tensorflow and PyTorch for classification, regression, textual and sequential analysis, and image recognition tasks.

The course covers the most important concepts of neural networks e.g. introduction to various neural network algorithms, differing network topologies, activation and loss functions, operations on tensors of varying dimensionality as well as more advanced multi-layered (deep) learning methods with Python including training, validation and optimisation of distributed neural network models with the h2o framework and deep learning applications with keras, PyTorch and tensorflow libraries. Examples of approaches include convolutional and recurrent neural networks, long short-term memory and selected generative deep learning models.

2. Programme.

The course will run for two days (Thursday and Friday) between 9:30am and 5:00pm and will consist of alternating lecture-style presentations and practical tutorials. The example datasets used during tutorial sessions will come from social sciences, psychology, business and finance fields, however the contents may vary depending on specific interests of participants (based on the Participant’s Skills Inventory). There will be two 15-minute coffee/tea breaks and one 1-hour lunch break on each day of the course.

The programme for this course covers the following concepts and topics:

• Introduction to artificial neural networks, multi-layer networks and deep learning – defining network components and topologies,
• Behaviour, structure and implementation of typical neural network algorithms e.g. backpropagation, feed-forward etc.; defining activation and loss functions for specific classification and predictive tasks,
• The logic and data representations of multi-layered artificial neural networks – from scalars, vectors and matrices to multi-dimensional tensors; tensor operations and transformations with NumPy, SciPy and scikit-learn libraries,
• Understanding of the machine and deep learning process – methods of data preparation and preprocessing, feature engineering, model training, validation and testing, regularisation techniques, model selection based on standard and custom-made evaluation metrics,
• An overview of deep learning requirements from the perspective of data processing architecture (RAM, CPUs, GPUs, cloud computing solutions etc.),
• Using h2o, keras and tensorflow Python packages for building and implementing neural networks and deep learning approaches for selected classification and regression tasks,
• Training, validation and optimisation of convolutional neural networks for image classification and recurrent neural networks for textual and sequential analysis with keras, PyTorch and tensorflow libraries,
• A comprehensive overview of more advanced deep learning methods with Python e.g. combined convolutional and recurrent neural networks, long short-term memory (LSTM) and generative models e.g. generative adversarial networks (GANs).

3. What is included?

Apart from the contents of the course, Mind Project will provide you with the following:

• printed course pack with all presentation slides, cheatsheets and other essential course information,

• digital (USB memory stick) Course Manual including all presentation slides, Python course code scripts (Jupyter notebooks) and a list of reference books and online resources,

• additional home exercises and all data sets available to download,

• stimulating, friendly and inclusive learning environment in a small group (typically 10-14 attendees) led by experienced and energetic tutors and course leaders,

• modern and comfortable training venue located in the heart of City of London – at the London Institute of Banking & Finance, next to the Monument underground station,

• refreshments and a light, energising lunch on each day of the course,

• Wi-Fi access,

• networking opportunity,

• Mind Project course attendance certificate.

4. Further instructions.

• In order to benefit from the course, we recommended that all attendees have the most recent version of Anaconda distribution of Python (by Continuum Analytics) installed on their laptops (any operating system). As Anaconda’s Python is a free and fully-supported distribution you can download it directly from https://www.continuum.io/downloads. Please contact us should you have any questions or issues with the installation process.

• Practical experience in data analytics using Python (e.g. pandas and NumPy libraries) and good knowledge of statistics is recommended for delegates attending this course. It is advisable that this course is preceded with our open-to-public “Python for Data Analysis” (https://www.mindproject.io/product/python-for-data-analysis-london-march-2019/) and “Machine Learning with Python” (https://www.mindproject.io/product/machine-learning-with-python-london-march-2019/) training courses.

• The deadline for registrations on this training course is Tuesday, 19th of March 2019 at 16:00 London (UK) time. Mind Project reserves the right to end the registration process earlier if all places are booked before the deadline.

Should you have any questions please contact Mind Project Ltd at info@mindproject.co.uk or by phone on 0203 322 3786. Please visit the course website at https://www.mindproject.io/product/deep-learning-with-python-london-march-2019/.

Cost:

£825 per person for the whole course (regular fee).
£675 per person for the whole course for UK registered undergraduate and postgraduate students, and representatives of registered charitable organisations (discounted fee).
For group bookings of 4 and more delegates, please contact us directly.

Website and registration:

https://www.mindproject.io/product/deep-learning-with-python-london-march-2019/

Region:

Greater London

Keywords:

Correlation, Effect size , Statistical Theory and Methods of Inference, Regression Methods, Data Mining, Neural networks, Machine learning, Mixed Methods Data Handling and Data Analysis, Quantitative Software, Python, Deep learning , Artificial Intelligence , Computer Vision , keras , tensorflow

Related publications and presentations:

Correlation
Effect size
Statistical Theory and Methods of Inference
Regression Methods
Data Mining
Neural networks
Machine learning
Mixed Methods Data Handling and Data Analysis
Quantitative Software
Python

Back to archive...