Neural Networks and Deep Learning Course: London


Register for Course
Https images 54974975 263404518528 1 original


Why this training?

This five-day hands-on course is designed for all those seeking a better understanding and knowledge of main technology trends driving deep learning.

Attendees will get a clear understanding of deep learning technology, practical scenarios to build, train and apply algorithms of fully connected deep neural networks, strategies to configure the key parameters in a neural network's architecture.

The participants will gain experience in building and applying deep neural networks, with most popular frameworks, such as Keras, TensorFlow, Theano, scikit-learn.

After the course, you will become fully skilled of implementing deep learning for your own applications.

Who should attend?

This course is a good fit for those seeking a better understanding and knowledge of:

the main technology trends driving deep learning

building, training, and applying fully connected deep neural networks

key parameters to optimize a neural network architecture

Course deliverables

During the course, the students will:

Gain understanding of deep learning concepts

Learn to use different types of neural networks

learn to build deep neural networks applications

As a result, at the end of the course participants will get real scripts, which can be used as a basis for creating algorithms that address specific business problems.

Certification: after participating in the course you will get a certificate of completion!


Day 1

Introduction to Deep Learning

Agenda for the training.

General introduction for neural networks and deep learning.

Neural Networks

History of neural networks

Components, perceptron

Multilayer perceptron / Feedforward Neural Networks

Layered structure, layers

Neural Network Zoo

Learning Neural Networks

Training scheme, holdout and cross-validation

Forward pass, case for use of GPU

Optimization task, SGD

Backward pass, error backpropagation

Activation function, ReLU, Sigmoid

Metric and loss function

Supervised, Unsupervised and Reinforcement Learning

Types of learning tasks

Supervised learning

Regression, quality metrics, MSE

Classification, quality metrics, LogLoss

Unsupervised Learning, clustering

Reinforced Learning overview

Day 2

Deep Learning in Computer Vision

Overview of image processing

Task variety in CV

Data gathering and preprocessing

FNN way to solve image classification, convolutions invariance

Convolutional Neural Networks

Convolution operation, gradients

Additional layers, flatten, pooling, dropout

CNN as a feature extractor for images

Image Classification

Task definition

Known benchmark datasets

Heavy architectures (ResNet, Inception)

Image Segmentation and Object Detection

Task definition


Transfer Learning

Pretrained Models

Universal property of low-level features

Layer freezing

Day 3

Deep Learning in Natural Language Processing

Problem specifics

Challenges in natural-language processing

Task examples: spam filtering, news flows classification, sentiment analysis, machine translation

Text Classification

Linear classifier

Naive Bayes

Bag of Words

Feedforward neural network over Bag of Words

Recurrent Neural Networks

RNN layer structure

Vanishing and exploding gradients

Long Short-Term Memory and Gated RecurrentUnit

Recurrent Neural Networks Applications

Language modeling

Sequence tagging

Machine translation

Dialog Systems

Architectures for dialog systems: input recognizer, dialog manager, task manager, output generator, output renderer

Types of systems and current frameworks

Time Series Prediction

Examples of Time Series and possible approaches to its processing

Autoregressive Models and Moving Average Models

Triple exponential smoothing

Day 4


Autoencoder structure

Training scheme

Dimensionality Reduction

Flavours of AE

Generative Adversarial Networks

GAN description, generator and discriminator

Error rates for ensemble

Day 5

Final project: Image Captioning


Altoros recommends that all students have:

Programming: Basic R and Python programming skills, with the capability to work effectively with data structures

Experience with the RStudio and the Jupyter Notebook applications

Basic experience with git

A basic understanding matrix vector operations and notation

A basic knowledge of Statistics

Basic command line operations

A workstation with the following capabilities:

A web browser (Chrome/Firefox)

Internet connection

A firewall allowing outgoing connections on TCP ports 80 and 443

The following developer utilities should be installed:



Jupyter Notebook

Register for Course

Don't See your Course?

Create a free course listing on Tech.London

Submit a Course


Get London tech news, jobs, and a preview of upcoming events straight to your inbox each week for free.