Here are some Good Learning Resource I found from the Internet. In RNN, we forward propagate, But we keep the information from the hidden layer for the second sample. The hidden layer for the second sample is a function of the new inputs, the updated weights, and the hidden layer from the previous iteration.

2020 was a tough year. Almost every seniors from our team graduated from 2019. We only have some final year students who picked robocon as final year project, which means they have little or no experence at all. When we finally came out some idea and want to try to prototype them, Siege of the Hong Kong Polytechnic University happened. My university were closed. Then the COVID-19 pandemic quickly arrives to Hong Kong and the school remained closed to everyone. Even professors have disallowed us to work at robotics lab. The progress was completely freezed for around six months. Many of our team members have slowly losing their ambitions.

墨香是我在小學的時侯玩的遊戲，是一隻以東方幻想武俠為題材的遊戲。這款遊戲是根據韓國同名小說改編。雖然遊戲已經很老了，但到今天仍有不少人玩這遊戲。暑假最後幾天，我決定回味下小學的回憶。

Generative Adversarial Networks (GANs) are a powerful type of neural network used for unsupervised learning. It involves automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset. GANs typically work with image data and use Convolutional Neural Networks, or CNNs, as the generator and discriminator models.

Generative Adversarial Networks (GANs) are a powerful type of neural network used for unsupervised learning. It involves automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset. GANs typically work with image data and use Convolutional Neural Networks, or CNNs, as the generator and discriminator models.

A regular expression is a sequence of characters that define a search pattern. It is quite useful when come to data cleaning. Since Regex techniques are mostly used while string manipulating. They are a domain specific language (DSL) that is present as a library in most modern programming languages, not just Python.

Transfer learning is a research problem in machine learning that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem. For example, knowledge gained while learning to recognize cars could apply when trying to recognize trucks.

Data augmentation is a strategy that enables practitioners to significantly increase the diversity of data available for training models, without actually collecting new data. Data augmentation techniques such as cropping, padding, and horizontal flipping are commonly used to train large neural networks.

CNN is mainly used in Image Recongition and deal with visual data. CNN's predictive power is much higher than NNs especially when it comes to image related problems.

CNN is mainly used in Image Recongition and deal with visual data. CNN's predictive power is much higher than NNs especially when it comes to image related problems.