-
Certificates: Deep Learning" certificate
-
Examination: Practical project work with final presentation
-
Teaching Times: Full-timeMonday to Friday from 8:30 a.m. to 3:35 p.m. (in weeks with public holidays from 8:30 a.m. to 5:10 p.m.)
-
Language of Instruction: German
-
Duration: 4 Weeks
Introduction to Deep Learning (approx. 1 day)
Deep learning as a type of machine learning
Fundamentals of neural networks (approx. 4 days)
Perceptron
Calculation of neural networks
Optimization of model parameters, backpropagation
Deep learning libraries
Regression vs. classification
Learning curves, overfitting and regularization
Hyperparameter optimization
Stochastic gradient descent (SGD)
Momentum, Adam Optimizer
Learning rate
Convolutional Neural Network (CNN) (approx. 2 days)
Image classification
Convolutional layers, pooling layers
Reshaping layers, flattening, global-average pooling
CNN architectures ImageNet-Competition
Deep neural networks, vanishing gradients, skip connections, batch normalization
Transfer Learning (approx. 1 day)
Adaptation of models
Unsupervised pre-training
Image data augmentation, explainable AI
Regional CNN (approx. 1 day)
Object localization
Regression problems
Branched neural networks
Methods of creative image generation (approx. 1 day)
Generative Adversarial Networks (GAN)
Deepfakes
Diffusion models
Recurrent neural networks (approx. 2 days)
Sequence analysis
Recurrent layers
Backpropagation through time (BPTT)
Analysis of time series
Exploding and vanishing gradient problems
LSTM (Long Short-Term Memory)
GRU (Gated Recurrent Unit)
Deep RNN
Deep LSTM
Text processing using neural networks (approx. 2 days)
Text preprocessing
Embedding layers
Text classification
Sentiment analysis
Transfer learning in NLP
Translations
Sequence-to-sequence method, encoder-decoder architecture
Language models (approx. 1 day)
BERT, GPT
Attention layers, Transformers
Text generation pipelines
Summarization
chatbots
Deep reinforcement learning (approx. 1 day)
Control of dynamic systems
Agent systems
Training through rewards
Policy Gradients
Deep Q-learning
Bayesian neural networks (approx. 1 day)
Uncertainties in neural networks
Statistical evaluation of forecasts
Confidence, standard deviation
Unbalanced data
Sampling methods
Project work (approx. 3 days)
To consolidate the content learned
Presentation of the project results
Changes are possible. The course content is updated regularly.
After the course, you will be familiar with the areas of application of deep learning and how neural networks work. You will understand how neural networks can recognize objects in images and will be able to provide machine learning and document processes.
Computer science, mathematics, electrical engineering and people with a degree in (business) engineering
Deep learning can be used to examine large amounts of data for patterns and models. This is why it is often used in the context of artificial intelligence for facial, object or speech recognition, for example in medical image recognition, text and speech recognition in sales, IT data security or monitoring financial transactions. Specialists with this knowledge can therefore be deployed in a variety of ways and are in high demand on the job market.
Your meaningful certificate provides a detailed insight into the qualifications you have acquired and improves your career prospects.
Didactic concept
Your lecturers are highly qualified both professionally and didactically and will teach you from the first to the last day (no self-study system).
You will learn in effective small groups. The courses usually consist of 6 to 25 participants. The general lessons are supplemented by numerous practical exercises in all course modules. The practice phase is an important part of the course, as it is during this time that you process what you have just learned and gain confidence and routine in its application. The final section of the course involves a project, a case study or a final exam.
Virtual classroom alfaview®
Lessons take place using modern alfaview® video technology - either from the comfort of your own home or at our premises at Bildungszentrum. The entire course can see each other face-to-face via alfaview®, communicate with each other in lip-sync voice quality and work on joint projects. Of course, you can also see and talk to your connected trainers live at any time and you will be taught by your lecturers in real time for the entire duration of the course. The lessons are not e-learning, but real live face-to-face lessons via video technology.
The courses at alfatraining are funded by Agentur für Arbeit and are certified in accordance with the AZAV approval regulation. When submitting a Bildungsgutscheinor Aktivierungs- und Vermittlungsgutschein, the entire course costs are usually covered by your funding body.
Funding is also possible via Europäischen Sozialfonds (ESF), Deutsche Rentenversicherung (DRV) or regional funding programs. As a regular soldier, you have the option of attending further training courses via Berufsförderungsdienst (BFD). Companies can also have their employees qualified via funding from Agentur für Arbeit (Qualifizierungschancengesetz).