Understand and build Deep Learning models for images, text and more using Python and Keras
InstructorData Weekends
Editorial course preview
These 4 complementary views highlight concrete, legible examples from the course presentation.
This Jupyter Notebook screenshot demonstrates how to load audio data using scipy.io and display it with an interactive audio player widget in Python.
This notebook cell demonstrates generating a synthetic moons dataset using scikit-learn and visualizing the resulting non-linearly separable data points.
This screenshot shows a Jupyter Notebook cell with Python code used to visualize model training history, specifically generating a loss curve graph that compares different batch sizes.
This screenshot displays a Jupyter Notebook cell containing Python code that generates a multi-line plot with four distinct colored data series for visualization.
Covers essential mathematical concepts including derivatives, the chain rule, and matrix notation alongside various architectures like CNNs and RNNs.
Utilizes a recurring pattern of presentation followed by solution videos to reinforce learning through hands-on exercises.
Multiple signals indicate that several exercise solutions are missing or remain marked as 'coming soon'.
The active learning path contains code that may produce errors in current environments due to outdated function calls and library versions.
Some technical details regarding function usage are glossed over, and the instructor's delivery can be difficult to follow for some learners.
The curriculum aligns with the target of intermediate learners, but signals suggest it may be too minimalistic for those without any machine learning background.