Deep Learning with Python
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 binary, multinomial 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.
By default, the course is implemented on CPU-based setup, however it is also possible to arrange this course to include GPU-run networks. Please let us know if you have any specific setup requirements.
Basic course information
Minimum recommended duration: 4-6 full days or 8-12 half-days (can be spread across multiple weeks)
Programming languages used: Python
Minimum number of attendees: 5
Course level: For intermediate users of Python and analysts with good understanding of maths and statistics, excellent as a “refresher” for experienced, senior analysts.
Pre-requisites: 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 the course is preceded with our “Applied Data Science with Python” and “Machine Learning with Python” courses.
IT recommendations: In order to benefit from the contents of the course it is recommended that 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 related to the installation process or should you wish to use a different setup for your course.
Programme outline
The programme for each in-house training course is discussed and agreed individually with the client. The proposed contents of the course may include (but is not limited to) 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. backgropagation, 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).
Customise the course
We can adapt our in-house training courses to address your specific needs and requirements e.g.:
The course can be designed to include your own data. If it is not possible e.g. due to data security issues, we can customise the course to contain exercises that address similar problems,
The course period can be spread across multiple weeks/months depending on your needs and availability – this will allow your delegates to revise and practise the learnt skills before the next session and provide them with additional time to internalise all presented material,
The course can include a custom project spread across several weeks/months with a follow-up session at the end of the period,
As all our in-house training courses are quoted individually, the final cost quotation will be based on several factors: the number of attendees, days of training (plus additional support/project guidance if needed), location of the training, complexity of IT setup and the extent of course customisation.
Arrange this course at your organisation
If you are interested in this in-house training course, please press Ask For Quote button in the top part of the page to enquire about and request a quote for this course based on your specific needs and desired outcomes of the training.
In your enquiry please include the following information:
contact details to a person who should receive the quote,
number of delegates you would like to train,
approximate number of days (or half-days) you would like to arrange the course for (including additional support/project guidance if needed),
location of the training venue,
any details on course customisation or specific topics you would like the course to address – most importantly, please indicate desired outcomes of the course if different then presented above,
any other questions you may have.
