Deep Learning Training in Belgrade

This instructor-led, live course in Belgrade (online or onsite) targets intermediate developers, data scientists, and AI professionals aiming to utilize TensorFlow Lite for Edge AI initiatives.

Upon completion of this training, participants will be able to:

• Comprehend the foundational aspects of TensorFlow Lite and its role in Edge AI.
• Build and optimize AI models using TensorFlow Lite.
• Deploy TensorFlow Lite models on diverse edge devices.
• Employ tools and techniques for model conversion and optimization.
• Develop practical Edge AI applications using TensorFlow Lite.

This instructor-led live training Belgrade (available online or on-site) targets advanced professionals who aim to deepen their grasp of computer vision and explore TensorFlow's capabilities for developing sophisticated vision models using Google Colab.

By the end of this training, participants will be able to:

• Build and train convolutional neural networks (CNNs) using TensorFlow.
• Leverage Google Colab for scalable and efficient cloud-based model development.
• Implement image preprocessing techniques for computer vision tasks.
• Deploy computer vision models for real-world applications.
• Use transfer learning to enhance the performance of CNN models.
• Visualize and interpret the results of image classification models.

This instructor-led, live training in Belgrade (online or onsite) is aimed at intermediate-level data scientists and developers who wish to understand and apply deep learning techniques using the Google Colab environment.

By the end of this training, participants will be able to:

• Set up and navigate Google Colab for deep learning projects.
• Understand the fundamentals of neural networks.
• Implement deep learning models using TensorFlow.
• Train and evaluate deep learning models.
• Utilize advanced features of TensorFlow for deep learning.

This instructor-led, live training in Belgrade (online or onsite) targets advanced-level professionals seeking to specialize in cutting-edge deep learning techniques for NLU.

By the end of this training, participants will be able to:

• Understand the key differences between NLU and NLP models.
• Apply advanced deep learning techniques to NLU tasks.
• Explore deep architectures such as transformers and attention mechanisms.
• Leverage future trends in NLU for building sophisticated AI systems.

Delivered as an instructor-led, live training in Belgrade (online or onsite), this course is designed for advanced professionals who wish to explore cutting-edge XAI techniques for deep learning models, focusing on the development of interpretable AI systems.

By the end of this training, participants will be able to:

• Understand the challenges of explainability in deep learning.
• Implement advanced XAI techniques for neural networks.
• Interpret decisions made by deep learning models.
• Evaluate the trade-offs between performance and transparency.

This instructor-led, live training in Belgrade (online or onsite) is designed for intermediate to advanced data scientists, machine learning engineers, deep learning researchers, and computer vision experts seeking to expand their knowledge and skills in deep learning for text-to-image generation.

Upon completion of this training, participants will be able to:

• Grasp advanced deep learning architectures and techniques for text-to-image generation.
• Implement complex models and optimizations for high-quality image synthesis.
• Enhance performance and scalability for large datasets and complex models.
• Tune hyperparameters to improve model performance and generalization.
• Integrate Stable Diffusion with other deep learning frameworks and tools

This instructor-led, live training in Belgrade (online or onsite) is tailored for advanced professionals who aim to leverage AI techniques to revolutionize drug discovery and development processes.

By the end of this training, participants will be able to:

• Understand the role of AI in drug discovery and development.
• Apply machine learning techniques to predict molecular properties and interactions.
• Use deep learning models for virtual screening and lead optimization.
• Integrate AI-driven approaches into the clinical trial process.

This instructor-led, live training in Belgrade (online or onsite) is designed for biologists who wish to understand how AlphaFold works and utilize AlphaFold models as guides in their experimental studies.

By the end of this training, participants will be able to:

• Understand the basic principles of AlphaFold.
• Learn how AlphaFold works.
• Learn how to interpret AlphaFold predictions and results.

This instructor-led, live training in Belgrade (online or onsite) is designed for beginner to intermediate data scientists and machine learning engineers who wish to improve the performance of their deep learning models.

Upon completion of this training, participants will be able to:

• Grasp the core principles of distributed deep learning.
• Install and configure DeepSpeed.
• Scale deep learning models on distributed hardware using DeepSpeed.
• Implement and experiment with DeepSpeed features to achieve optimization and memory efficiency.

This instructor-led, live training in Belgrade (online or onsite) is aimed at beginner-level to intermediate-level developers who wish to use Large Language Models for various natural language tasks.

By the end of this training, participants will be able to:

• Set up a development environment that includes a popular LLM.
• Create a basic LLM and fine-tune it on a custom dataset.
• Use LLMs for different natural language tasks such as text summarization, question answering, text generation, and more.
• Debug and evaluate LLMs using tools such as TensorBoard, PyTorch Lightning, and Hugging Face Datasets.

This instructor-led, live training (online or onsite) is aimed at data scientists, machine learning engineers, and computer vision researchers who wish to leverage Stable Diffusion to generate high-quality images for a variety of use cases.

By the end of this training, participants will be able to:

• Understand the principles of Stable Diffusion and how it works for image generation.
• Build and train Stable Diffusion models for image generation tasks.
• Apply Stable Diffusion to various image generation scenarios, such as inpainting, outpainting, and image-to-image translation.
• Optimize the performance and stability of Stable Diffusion models.

In this live, instructor-led training in Belgrade, participants will explore the most current and advanced machine learning techniques in Python by developing a series of demonstration applications that utilize image, audio, text, and financial data.

Upon completion of this training, participants will be able to:

• Implement machine learning algorithms and techniques to address complex problems.
• Apply deep learning and semi-supervised learning methods to applications involving images, music, text, and financial data.
• Maximize the potential of Python algorithms.
• Utilize libraries and packages such as NumPy and Theano.

This four-day course provides an introduction to Artificial Intelligence and its practical applications using the Python programming language. Upon completing the course, there is an option to dedicate an additional day to working on a hands-on AI project.

Deep Reinforcement Learning (DRL) merges reinforcement learning principles with deep learning architectures, allowing agents to make decisions through interaction with their environments. This technology supports many modern AI advancements, including self-driving vehicles, robotics control, algorithmic trading, and adaptive recommendation systems. DRL enables artificial agents to learn strategies, optimize policies, and make autonomous decisions based on trial-and-error reward-based learning.

This instructor-led live training (available online or onsite) targets intermediate-level developers and data scientists who want to learn and apply Deep Reinforcement Learning techniques to build intelligent agents capable of autonomous decision-making in complex environments.

By the end of this training, participants will be able to:

• Grasp the theoretical foundations and mathematical principles of Reinforcement Learning.
• Implement key RL algorithms, including Q-Learning, Policy Gradients, and Actor-Critic methods.
• Build and train Deep Reinforcement Learning agents using TensorFlow or PyTorch.
• Apply DRL to real-world applications such as games, robotics, and decision optimization.
• Troubleshoot, visualize, and optimize training performance using modern tools.

Format of the Course

• Interactive lecture and guided discussion.
• Hands-on exercises and practical implementations.
• Live coding demonstrations and project-based applications.

Course Customization Options

• To request a customized version of this course (e.g., using PyTorch instead of TensorFlow), please contact us to arrange.

In this instructor-led, live training in Belgrade, participants will learn how to implement deep learning models for the telecom sector using Python by stepping through the creation of a deep learning credit risk model.

By the end of this training, participants will be able to:

• Grasp the fundamental concepts of deep learning.
• Explore the applications and uses of deep learning in telecom.
• Utilize Python, Keras, and TensorFlow to develop deep learning models for telecom.
• Construct their own deep learning customer churn prediction model using Python.

Designed for managers, solutions architects, innovation officers, CTOs, software architects, and anyone curious about applied artificial intelligence and its near-term trajectory, this course provides a comprehensive overview.

This course provides an overview of AI, with a focus on Machine Learning and Deep Learning, within the Automotive sector. It enables participants to identify which technologies can be (potentially) applied in various car scenarios, ranging from basic automation and image recognition to autonomous decision-making.

This instructor-led, live training in Belgrade (online or onsite) is aimed at beginner-level participants who wish to learn essential concepts in probability, statistics, programming, and machine learning, and apply these to AI development.

By the end of this training, participants will be able to:

• Understand basic concepts in probability and statistics, and apply them to real-world scenarios.
• Write and understand procedural, functional, and object-oriented programming code.
• Implement machine learning techniques such as classification, clustering, and neural networks.
• Develop AI solutions using rules engines and expert systems for problem-solving.

Artificial Neural Networks (ANNs) are computational models designed for developing Artificial Intelligence (AI) systems that can perform complex, "intelligent" tasks. These networks are widely utilized in Machine Learning (ML) applications, which represent one of the primary implementations of AI. Deep Learning constitutes a specialized subset within the broader field of Machine Learning.

This four-day course provides an introduction to Artificial Intelligence and its practical applications. Upon completing the course, participants have the option to dedicate an additional day to working on a dedicated AI project.

This instructor-led live training in Belgrade (online or onsite) is designed for intermediate-level data scientists and statisticians aiming to prepare data, build models, and effectively apply machine learning techniques in their professional roles.

By the end of this training, participants will be able to:

• Understand and implement various Machine Learning algorithms.
• Prepare data and models for machine learning applications.
• Conduct post hoc analyses and visualize results effectively.
• Apply machine learning techniques to real-world, sector-specific scenarios.

An Artificial Neural Network is a computational data model utilized in creating Artificial Intelligence (AI) systems that can execute "intelligent" tasks. These networks are frequently employed within Machine Learning (ML) applications, which represent one form of AI implementation. Deep Learning constitutes a specialized subset of ML.

This instructor-led, live training in Belgrade (online or onsite) is aimed at researchers and developers who wish to use Chainer to build and train neural networks in Python while making the code easy to debug.

By the end of this training, participants will be able to:

• Set up the necessary development environment to start developing neural network models.
• Define and implement neural network models using a comprehensible source code.
• Execute examples and modify existing algorithms to optimize deep learning training models while leveraging GPUs for high performance.

This instructor-led, live training in Belgrade (online or onsite) offers an introduction to the fields of pattern recognition and machine learning. It covers practical applications in statistics, computer science, signal processing, computer vision, data mining, and bioinformatics.

By the end of this training, participants will be able to:

• Apply core statistical methods to pattern recognition.
• Use key models like neural networks and kernel methods for data analysis.
• Implement advanced techniques for complex problem-solving.
• Improve prediction accuracy by combining different models.

This course provides a broad overview of Deep Learning without delving excessively into any specific methodologies. It is ideal for individuals looking to begin leveraging Deep Learning to improve their prediction accuracy.

This instructor-led live training in Belgrade (online or onsite) targets researchers and developers who wish to install, set up, customize, and utilize the DeepMind Lab platform to develop general artificial intelligence and machine learning systems.

By the end of this training, participants will be able to:

• Customize DeepMind Lab to build and run an environment that suits learning and training needs.
• Use DeepMind Lab's 3D simulation environment to train learning agents in a first-person viewpoint.
• Facilitate agent evaluation to develop intelligence in a 3D game-like world.

Machine learning is a branch of Artificial Intelligence wherein computers have the ability to learn without being explicitly programmed. Deep learning is a subfield of machine learning which uses methods based on learning data representations and structures such as neural networks.

This live, instructor-led training in Belgrade (online or on-site) is tailored for business analysts, data scientists, and developers who aim to create and implement deep learning models to boost revenue growth and solve business problems.

By the end of this course, participants will be able to:

• Understand the core concepts of machine learning and deep learning.
• Gain insights into the future of business and industry with ML and DL.
• Define business strategies and solutions with deep learning.
• Learn how to apply data science and deep learning in solving business problems.
• Build deep learning models using Python, Pandas, TensorFlow, CNTK, Torch, Keras, etc.

In this instructor-led live training in Belgrade, participants will learn to utilize Python libraries for NLP by building an application that processes images and generates captions.

By the end of this training, participants will be able to:

• Design and code Deep Learning for NLP using Python libraries.
• Create Python code that processes a large volume of images and generates keywords.
• Produce Python code that generates captions from the identified keywords.

Audience

This course is designed for researchers and engineers in the field of Deep Learning who wish to leverage available tools, primarily open-source solutions, for the analysis of computer images.

Participants will engage with practical working examples.

This instructor-led, live training in Belgrade (online or onsite) targets data scientists who wish to accelerate real-time machine learning applications and deploy them at scale.

By the end of this training, participants will be able to:

• Install the OpenVINO toolkit.
• Speed up computer vision applications using an FPGA.
• Run different CNN layers on the FPGA.
• Scale the application across multiple nodes in a Kubernetes cluster.

This instructor-led live training in Belgrade (online or on-site) is designed for data scientists who want to use TensorFlow to analyze potential fraud data.

By the end of this training, participants will be able to:

• Create a fraud detection model in Python and TensorFlow.
• Build linear regressions and linear regression models to predict fraud.
• Develop an end-to-end AI application for analyzing fraud data.

This instructor-led live training in Belgrade (online or onsite) is targeted at developers and data scientists who wish to use Horovod for distributed deep learning and scale it across multiple GPUs in parallel.

By the end of this training, participants will be able to:

• Set up the necessary development environment to begin running deep learning trainings.
• Install and configure Horovod to train models with TensorFlow, Keras, PyTorch, and Apache MXNet.
• Scale deep learning training using Horovod across multiple GPUs.

This instructor-led live training in Belgrade (online or onsite) is designed for technical professionals looking to apply deep learning models to image recognition applications.

Upon completion of this training, participants will be capable of:

• Installing and configuring Keras.
• Rapidly prototyping deep learning models.
• Implementing a convolutional network.
• Implementing a recurrent network.
• Running deep learning models on both CPU and GPU architectures.

In this instructor-led live training, participants will learn how to use Matlab to design, build, and visualize a convolutional neural network for image recognition.

By the end of this training, participants will be able to:

• Build a deep learning model
• Automate data labeling
• Work with models from Caffe and TensorFlow-Keras
• Train data using multiple GPUs, the cloud, or clusters

Audience

• Developers
• Engineers
• Domain experts

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

This instructor-led, live training in Belgrade (online or onsite) is designed for professionals at beginner to intermediate levels who aim to enhance their comprehension of machine learning algorithms, deep learning methodologies, and AI-driven decision strategies. The curriculum offers practical experience with core machine learning concepts, deep learning architectures, and real-world implementations utilizing the R programming language.

Upon completion of this training, participants will be able to:

• Grasp the fundamental principles of machine learning and deep learning.
• Apply diverse machine learning algorithms for regression, classification, clustering, and anomaly detection tasks.
• Utilize deep learning architectures, including Artificial Neural Networks (ANNs).
• Develop both supervised and unsupervised learning models.
• Assess model performance and fine-tune hyperparameters.
• Leverage R for data analysis, visualization, and implementing machine learning solutions.

The course is designed for individuals interested in learning the fundamentals of neural networks and their practical applications.

This instructor-led training session integrates presentations with hands-on computer-based examples and case study exercises using relevant neural and deep learning libraries.

This instructor-led, live training in Belgrade (online or onsite) is aimed at software engineers who wish to program in Python with OpenCV 4 for deep learning.

By the end of this training, participants will be able to:

• View, load, and classify images and videos using OpenCV 4.
• Implement deep learning in OpenCV 4 with TensorFlow and Keras.
• Run deep learning models and generate impactful reports from images and videos.

During this instructor-led, live training, participants will acquire advanced techniques for Machine Learning using R while building a real-world application step-by-step.

Upon completing this course, participants will be capable of:

• Grasping and implementing unsupervised learning techniques
• Utilizing clustering and classification methods to generate predictions from real-world data
• Visualizing data to rapidly extract insights, inform decisions, and further refine analysis
• Enhancing machine learning model performance through hyper-parameter tuning
• Deploying models into production for integration into larger applications
• Applying advanced machine learning techniques to address challenges related to social network data, big data, and other domains

This course provides an introduction to utilizing neural networks for solving real-world challenges with the R programming environment.

This instructor-led, live training Belgrade (online or onsite) is designed for developers and data scientists interested in utilizing TensorFlow 2.x to build predictors, classifiers, generative models, neural networks, and other solutions.

By the end of this training, participants will be able to:

• Install and configure TensorFlow 2.x.
• Understand the benefits of TensorFlow 2.x over previous versions.
• Build deep learning models.
• Implement an advanced image classifier.
• Deploy a deep learning model to the cloud, mobile and IoT devices.

This instructor-led, live training in Belgrade (online or onsite) targets engineers who wish to write, load, and run machine learning models on very small embedded devices.

By the end of this training, participants will be able to:

• Install TensorFlow Lite.
• Load machine learning models onto an embedded device to enable it to detect speech, classify images, etc.
• Add AI to hardware devices without relying on network connectivity.

In this instructor-led live training in Belgrade (online or onsite), participants will learn how to configure and use TensorFlow Serving to deploy and manage ML models in a production environment.

By the end of this training, participants will be able to:

• Train, export and serve various TensorFlow models.
• Test and deploy algorithms using a single architecture and set of APIs.
• Extend TensorFlow Serving to serve other types of models beyond TensorFlow models.

TensorFlow is the second-generation API of Google’s open-source library for Deep Learning. The system is designed to facilitate machine learning research and enable a rapid transition from research prototypes to production systems.

Audience

This course is intended for engineers who wish to apply TensorFlow to their Deep Learning projects.

After completing this course, delegates will be able to:

• Understand the architecture and deployment mechanisms of TensorFlow
• Perform installation tasks, configure the production environment, and set up the architecture
• Assess code quality, debug, and monitor performance
• Implement advanced production-level tasks, such as training models, building graphs, and logging

This course provides a detailed examination of how TensorFlow is applied in the field of image recognition, illustrated through concrete examples.

Target Audience

The course is designed for engineers who wish to leverage TensorFlow for image recognition tasks.

Learning Outcomes:

• Gain a clear understanding of TensorFlow’s structure and deployment mechanisms
• Perform installation, set up production environments, and configure architecture
• Assess code quality, conduct debugging, and implement monitoring practices
• Execute advanced production tasks such as model training, graph construction, and logging

This instructor-led live training in Belgrade (online or onsite) is designed for data scientists seeking to expand their skills from training single ML models to deploying multiple models in production.

By the end of this training, participants will be able to:

• Install and configure TFX and its supporting third-party tools.
• Use TFX to create and manage a complete ML production pipeline.
• Leverage TFX components to perform modeling, training, inference serving, and deployment management.
• Deploy machine learning features across web applications, mobile applications, IoT devices, and more.

TensorFlow™ is an open-source software library designed for numerical computation via data flow graphs.

SyntaxNet serves as a neural-network-based Natural Language Processing framework for TensorFlow.

Word2Vec is utilized for learning vector representations of words, known as 'word embeddings'. It is a highly computationally efficient predictive model for deriving word embeddings from raw text. It offers two variants: the Continuous Bag-of-Words model (CBOW) and the Skip-Gram model (refer to Chapters 3.1 and 3.2 in Mikolov et al.).

By combining SyntaxNet and Word2Vec, users can generate learned embedding models from Natural Language inputs.

Audience

This course is designed for developers and engineers who plan to work with SyntaxNet and Word2Vec models within their TensorFlow graphs.

Upon completion of this course, participants will be able to:

• understand the structure and deployment mechanisms of TensorFlow
• execute installation, production environment setup, architecture tasks, and configuration
• assess code quality, perform debugging, and monitor performance
• implement advanced production-like activities such as training models, embedding terms, building graphs, and logging

This program initiates with conceptual knowledge in neural networks and generally in machine learning algorithms, deep learning (algorithms and applications).

Part-1(40%) of this training is more focus on fundamentals, but will help you choosing the right technology : TensorFlow, Caffe, Theano, DeepDrive, Keras, etc.

Part-2(20%) of this training introduces Theano - a python library that makes writing deep learning models easy.

Part-3(40%) of the training would be extensively based on Tensorflow - API of Google's open source software library for Deep Learning. The examples and handson would all be made in TensorFlow.

Audience

This course is intended for engineers seeking to use TensorFlow for their Deep Learning projects

After completing this course, delegates will:

• have a good understanding on deep neural networks(DNN), CNN and RNN
• understand TensorFlow’s structure and deployment mechanisms
• be able to carry out installation / production environment / architecture tasks and configuration
• be able to assess code quality, perform debugging, monitoring
• be able to implement advanced production like training models, building graphs and logging