Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Supervised learning: classification and regression
- Machine Learning in Python: Introduction to the scikit-learn API
- linear and logistic regression
- support vector machines
- neural networks
- random forests
- Establishing an end-to-end supervised learning pipeline with scikit-learn
- manipulating data files
- imputing missing values
- processing categorical variables
- visualizing data
Python frameworks for AI applications:
- TensorFlow, Theano, Caffe, and Keras
- Scaling AI with Apache Spark MLlib
Advanced neural network architectures
- Convolutional neural networks for image analysis
- Recurrent neural networks for time-series data
- Long short-term memory (LSTM) cells
Unsupervised learning: clustering and anomaly detection
- Implementing principal component analysis with scikit-learn
- Building autoencoders in Keras
Practical examples of solvable AI problems (hands-on exercises via Jupyter notebooks), e.g.
- image analysis
- forecasting complex financial time series, such as stock prices
- complex pattern recognition
- natural language processing
- recommender systems
Understanding the limitations of AI methods: failure modes, costs, and common challenges
- overfitting
- the bias/variance trade-off
- biases within observational data
- neural network poisoning
Applied Project work (optional)
Requirements
No specific prerequisites are required to enroll in this course.
28 Hours
Testimonials (2)
That it was applying real company data. Trainer had a very good approach by making trainees participate and compete
Jimena Esquivel - Zaklad Uslugowy Hakoman Andrzej Cybulski
Course - Applied AI from Scratch in Python
The trainer was a professional in the subject field and related theory with application excellently
