Repository for storing and tracking my self-study progress.
This is a repository that I have created to track my progress in AI/Data Science related topics in order to organise my knowledge and goals. Purpose of doing this is self-motivation, open source/study material for others, portfolio and TODO list.
| Presentation | Where | Date | Slides | | :---: | :---: | :---: | :---: | | Welcome to MOOC era! - My experiences with Deep Learning Foundations Nanodegree at Udacity | Speaker - GDG & Women Techmakers - Machine Learning #3 | 18.10.2017 | Link | | Soft introduction into MSE based Linear Regression (part 2 of 'What this Machine Learning is all about?' talk) | Azimo Lunch & Learn | 16.11.2017 | Link | | Advantages of Batch Normalization in Deep Learning | PyData Warsaw, Let’s meet to talk about AI in Bialystok #2 | 10.04.2018, 01.06.2018 | Link |
In this section I will focus about digging up relationship and visualising data. I will try to use Machine learning and visualisation methods for problem solving.
| Problem | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | | Prediction of Bike Shop Clients Number | Used MLP with 1-layer, mini-batch | Python (numpy, matplotlib) | Bike-Sharing | 13.08.2017 | 13.08.2017 | | Kaggle - Titanic Disaster survivor prediction | Used Logistic Regression with ~80% accuracy | Python (raw) | Titanic Disaster | 19.10.2017 | 24.10.2017 |
| Problem | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | | Picking best computer game to try| Used K-Means Clusters for visualising top positions | Python (raw) | Kaggle - Video Game Sales | 01.10.2017 | 05.10.2017 |
In this section I want to show off my knowledge about various AI related algorithms, frameworks, programming languages, libraries and more. Priority is to show how the algorithm works - not to solve complex and ambitious problems. Usually on classical or generated datasets.
| Algorithm | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | | Linear Regression | - | Python (raw) | Generated Numbers | 18.04.2017 | 15.09.2017 | | Ridge Regression | Compared result with Linear Regression | Python (raw) | Generated Numbers | 23.09.2017 | 23.09.2017 | | Polynomial Regression | Approximating Polynomial of degree 2 | Python (raw) | Generated Numbers | 08.06.2017 | 15.09.2017 | | Polynomial Regression | Approximating Polynomial of degree 3 | Python (raw) | Generated Numbers | 10.06.2017 | 15.09.2017 | | KNN | Manhattan, Euclidean Similarity | Python (raw) | iris | 21.07.2017| 24.09.2017 | | PCA | - | Python (raw) | Generated Numbers | 01.04.2017 | 23.09.2017 | | Naive Bayes | Gaussian Distribution | Python (raw) | Pima Indian Diabetes | 02.11.2017 | 03.11.2017 |
| Net Type | Problem | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | MLP | Digit Classification | 2-layers, mini-batch | Python (raw) | MNIST | 19.06.2017 | 14.08.2017 |
| Algorithm | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | | Linear Regression | - | Python (sklearn) | Generated Numbers | 18.04.2017 | 15.09.2017 | | Polynomial Regression | Approximating Polynomial of degree 2 | Python (sklearn) | Generated Numbers | 10.06.2017 | 15.09.2017 | | Polynomial Regression | Approximating Polynomial of degree 3 | Python (sklearn) | Generated Numbers | 10.06.2017 | 15.09.2017 | | KNN | Euclidean Similarity | Python (sklearn) | iris | 22.07.2017 | 24.09.2017 |
| Algorithm | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | | Linear Regression | - | Python (Tensorflow) | Generated Numbers | 23.09.2017 | 23.09.2017 |
| Net Type | Problem | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | MLP | Digit Classification | 2-layers, mini-batch, dropout-regularization | Python (Tensorflow) | MNIST | 29.06.2017 | 18.07.2017 | | MLP | Encrypting data with Autoencoder | 1-layer Encoder, 1-layer Decoder, mini-batch | Python (Tensorflow) | MNIST | 13.07.2017 | 13.07.2017 | | MLP | Digit Classification | tf.layer module, dropout regularization, batch normalization | Python (Tensorflow) | MNIST| 16.08.2017 | 23.08.2017 | | CNN | 10 Classes Color Images Classification | tf.nn module, dropout regularization | Python (Tensorflow) | CIFAR-10 | 16.08.2017 | 07.09.2017 | | CNN | 10 Classes Color Images Classification | tf.layer module, dropout regularization | Python (Tensorflow) | CIFAR-10 | 16.08.2017 | 09.09.2017 | | CNN | 10 Classes Color Images Classification | tf.layer module, dropout regularization, batch normalization | Python (Tensorflow) | CIFAR-10 | 19.08.2017 | 10.09.2017 | | RNN | Simple Language Translator | In form of my DLFND project for now | Python (Tensorflow) | Small part of French-English corpus | 05.05.2017 | 24.05.2017 | | RNN | "The Simpsons" Script Generation | In form of my DLFND project for now | Python (Tensorflow) | "The Simpsons" script | 06.06.2017 | 14.07.2017 | | DCGAN | Generating Human Face Miniatures | DCGAN | Python (Tensorflow) | CelebA | 11.09.2017 | 13.09.2017 |
| Net Type | Problem | Description | Implementation | Dataset | Creation Date | Last Update | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | MLP | Digit Classification | 2-layers, mini-batch, BN | Python (Keras) | MNIST | 10.03.2018 | 10.03.2018 | | MLP | Clothes Images Classification | 2-layers, mini-batch, BN | Python (Keras) | Fashion MNIST | 15.04.2018 | 15.04.2018 | | MLP | Letters Classification | 2-layers, mini-batch, BN | Python (Keras) | EMNIST | 24.04.2018 | 24.04.2018 | | MLP | Review Sentiment Classification | Bag of Words | Python (Keras) | IMDB Reviews | 11.03.2018 | 11.03.2018 | | MLP | Boston House Prices Regression | 1 layer, mini-batch | Python (Keras) | Boston House Prices | 19.04.2018 | 19.04.2018 | | CNN | Ten Color Image Classes Classification | VGG15 | Python (Keras) | CIFAR10 | 27.03.2018 | 27.03.2018 | | CNN | Letter Classification | 32x32x64x64, 512, BN | Python (Keras) | EMNIST | 25.03.2018 | 23.03.2018 | | CNN | Clothes Images Classification | 16x16x32x32, 256x128, BN | Python (Keras) | Fashion MNIST | 11.03.2018 | 11.03.2018 | | CNN | Digit Classification | 16x32x64, 128, BN| Python (Keras) | MNIST | 24.03.2018 | 24.03.2018 | | RNN | Next Month Prediction | LSTM(128) | Python (Keras) | Month Order | 15.04.2018 | 15.04.2018 | | RNN | Shakespeare Sonnet's Generation | LSTM(700), LSTM(700) | Python (Keras) | Shakespeare's sonnets | 17.04.2018 | 17.04.2018 |
Note: Delayed due to 1,5 month long preparations for organising ML/DL workshops.
| Title | Link | Jupyter | Publsh Date | Update Date | | :---: | :---: | :---: | :---: | :---: | | Coding Deep Learning for Beginners — Start! | Medium | - | 12.02.2018 | 12.02.2018 |
When I was younger I played a lot of computer games. I still tend to play today a little as a form of relax and to spend time with friends that live far from me. One thing that I have very enjoyed about gaming was gathering trophies. You made an effort to complete list of challenges or get a great score and then looked at list of your achievements with satisfaction. My current self have inherited this habit and as I study on daily basis I like to gather proves that I have done something - to make it more like a game where each topic is a boss that you have to clear on hard mode. Of course what's in your head is most important but if it helps to motivate you, then why not?
Programming languages:
Algorithms:
AI related:
There is a list of sources that I have used (and found helpful in some way) or keep using in order to produce my repo content.