This lecture is about basics of the tensorflow, we will discuss the minimal example on the MNIST dataset. We also investigate a meaning of the validation sets and different complexity of the model.
This lecture is about introduction to CNNs.
We use validating sets, and evaluate our models on CIFAR-10 dataset.
Also we will also try Batch normalization layer in Keras.
This lecture is focused in more detailed understanding of the Convolution neural networks.
The visualization and the response of the CNN layers will be intestigated and a proper.
We will use the MNIST dataset but other may be used as well.
This lecture is focused on the more advanced examples of the RNN usage for text data anylysis.
We will deal with the sentiment analysis task using Twitter data.
This lecture is focused on the more advanced examples of the RNN usage for text generation.
We will use Harry Potter books in this lectures for generating our own stories.
This lecture is about the time series forecasting utilizing deep learning. We will discuss the natural gas consumption forecasting topic using provided dataset as in on of the previous lectures.
his lecture is focused on using CNN for object localization tasks.
This lecture is focused on Generative Adversarial Networks for image generation.
A generative adversarial network (GAN) is deployed to create unique images of handwritten digits. The generated images look like they're taken from the dataset (that is the purpose), but they are generated from scratch (actually, from noise) and are all unique.