Skip to content

bumpy road to code

personal path to master code

Home
C++
C#
- The Nature of Code [C#]
- Unity Game Dev [C#]
Python
- Machine Learning A-Z Menu
Bookshelf
Hardware
About

BRTC Makeover!

bumpyroadtocode Blog January 21, 2019January 21, 2019 1 Minute

bumpy road to code [BRTC] gets a makeover, new color scheme and logo, yay!
Also, yes I have neglected my code-blog for a while, its true, I have been massively busy, but I believe I can do better in the future, I promise 🙂

Share this:

Twitter
Facebook

Like this:

Like Loading...

Related

Published by bumpyroadtocode

View all posts by bumpyroadtocode

Published January 21, 2019January 21, 2019

Post navigation

Previous Post Machine Learning A-Z [WIP]

Next Post Galaxy Shooter [Unity & WebGL]

Leave a Reply Cancel reply

Enter your comment here...

Fill in your details below or click an icon to log in:

Email (required) (Address never made public)

Name (required)

Website

You are commenting using your WordPress.com account. ( Log Out / Change )

You are commenting using your Google account. ( Log Out / Change )

You are commenting using your Twitter account. ( Log Out / Change )

You are commenting using your Facebook account. ( Log Out / Change )

Connecting to %s

Notify me of new comments via email.

Notify me of new posts via email.

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Follow me on Twitter

Follow me on Instagram

Machine Learning Model Reinforcement Learning . :: Reinforcement Learning is by far the most exciting and probably currently the hottest topic in the world of Machine Learning and Artificial Intelligence. At least I think so. Specifically @Google DeepMind has made quite some waves with their chess- and go-master beating AlphaGo and it's successor AlphaZero. But also OpenAi and their StarCraft Algorithm has managed to get quite some attention. Quite recently they actually published my currently favourite video out there, explaining their most recent developments using a hide and seek game. Imagine what else such an agent could "play" and master. There could be more complex environments and higher complexity of rules for example in the real world - so really, playing board games is just the beginning... . :: I will try to keep this as high level as possible. Of course, this could be loaded with a bunch of expert knowledge and words nobody understands. But the fundamental operation of a reinforcement learning agent is as follows: There is a given environment, the environment is in a specific state in time (St), the agent has the ability to understand the state of the environment and according to this specific state in time, it is considering possible actions and takes the most reasonable one in time (At), because of the action of the agent, the environment might have changed, so the state (St) gets an update (St+1), and the environment also gives the agent a reward for its previous action (Rt+1), the reward could be negative or positive, depending how the state of the environment has changed according to the action of the agent. So the interesting and difficult part becomes the design of the reward function. . #artificialintelligence #machinelearning #ai #ml #data #reinforcementlearning #rl #agent #state #environment #selflearning #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics

Machine Learning Model K-Nearest Neighbor Classification . :: K-Nearest Neighbor seems to be easily graspable in a 2d or even 3 dimensions since the euclidean distance is something we are dealing with in everyday life and is easily relatable to the physical world. . :: This is how the algorithm works: 1. Add new data points to your scatter plot of already labelled data, as seen above 2. Choose the number K of neighbors 3. Take the K nearest neighbors of the new data point, according to the Euclidean distance 4. Among these K neighbors, count the number of data points in each category 5. Assign the new data point to the category where you counted the most neighbors . #artificialintelligence #machinelearning #ai #ml #data #knearestneighbor #classification #knn #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics

Learning: Unsupervised, Supervised and Reinforcement (RL) . :: I have found this diagram in one of „Lazy Programmer“‘s videos on Udemy and just really liked the simplicity of it. Also I have been developing a strong interest for unsupervised learning and even more so for reinforcement learning. I just find the works of @google deepMind extremely fascinating. So stay tuned for more RL content in the future. . #dataanalytics #machinelearning #artificialintelligence #statistics #data #ai #datamining #neurocomputing #datascience #patternrecognition #reinforcementlearning #supervisedlearning #unsupervisedlearning #learning

Machine Learning Model Logistic Regression Classification . :: This is the second pos ton logistic regression classification, but in a lower technical level. It is a very powerful classification method, especially for decision driven applications. . :: The black dots are representing the dataset. The red line diagonally through the graph is representing the linear regression line of the given data - combined with a sigmoid function, the regression curve changes to logistic regression. Three further data points are introduced to predict the dependend variable y, which in this case is "Yes" or "No", as well as a probabilistic value 0 to 100%. . :: Neural networks are somewhat related to logistic regression. Basically, we can think of logistic regression as a one layer neural network. . #artificialintelligence #machinelearning #ai #ml #data #logisticregression #regression #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics #neuralnetwork

How Artificial Intelligence, Machine Learning and Deep Learning integrate. . :: "Artificial intelligence (AI) makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks. Most AI examples that you hear about today – from chess-playing computers to self-driving cars – rely heavily on deep learning and natural language processing. Using these technologies, computers can be trained to accomplish specific tasks by processing large amounts of data and recognizing patterns in the data." - SAS . :: This is the second post to untangle the differences between AI, ML and DL. As the diagram shows, Artificial Intelligence is the paradigm or a collection of techniques for machines to learn and use the knowledge to solve problems autonomously. Machine Learning is one of those techniques and subsequently, Deep Learning is a Machine Learning Method, next to Unsupervised and Supervised Learning. . #artificialintelligence #machinelearning #deeplearning #ai #ml #dl #data #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics #supervisedlearning #unsupervisedlearning #naturallanguageprocessing #nlp #expertsystems #vision #speech #planning #robotics #contentextraction #classification #machinetranslation #questionanswering #textgeneration #imagerecognition #machinevision

Machine Learning Model Random Forest Regression Regression . :: Random Forest Regression is one of the most powerful regression models out there. You can use either multiple algorithms or the same algorithm multiple times to make a more powerful model then your original. . :: In the example above, for simplicity, I chose to use multiple decision tree algorithms. The dataset is divided into subsets and each subset is training a tree. For the prediction step, the same data is passed through all trees and the average of the single tree y is taken as the resulting y. . :: At least take 500 trees for your forest, which means you will end up with 500 predictions for the one data point in question (x1), this is very powerful! . #artificialintelligence #machinelearning #ai #ml #data #randomforestregression #decisiontreeregression #regression #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics

Machine Learning VS Deep Learning . :: @nvidia Michael Copeland „Artificial intelligence is the future. Artificial intelligence is science fiction. Artificial intelligence is already part of our everyday lives. All those statements are true, it just depends on what flavor of AI you are referring to. . For example, when Google DeepMind’s AlphaGo program defeated South Korean Master Lee Se-dol in the board game Go earlier this year, the terms AI, machine learning, and deep learning were used in the media to describe how DeepMind won. And all three are part of the reason why AlphaGo trounced Lee Se-Dol. But they are not the same things. . The easiest way to think of their relationship is to visualize them as concentric circles with AI — the idea that came first — the largest, then machine learning — which blossomed later, and finally deep learning — which is driving today’s AI explosion — fitting inside both.“ . #machinelearning #deeplearning #neuralnetworks #perceptron #learning #arificialintelligence #data #featureextraction #classification #datascience #dataprocessing #patternrecognition #statistics #statisticalmodelling #kdd #databases #ai #datamining #neurocomputing #patternrecognition

Machine Learning Model Multiple Linear Regression . :: Multiple Linear Regression is quite an exciting machine learning model. Instead of looking into one independent variable and one dependent variable, we can look into multiple independent variables, like in the example above experience x1 and age x2 to predict the dependent variable salary y. I chose to only use two independent variables because this allows me to represent the model in a three-dimensional space. Of course, Multiple Linear Regression gets more exciting with many more independent variables, especially looking into variable coefficients, which determines a weight for the variable, indicating how important one independent variable is or furthermore exploring ways of dimensionality reduction, once we have too many independent variables and we need to figure out which are the most impactful independent variables. . #artificialintelligence #machinelearning #ai #ml #data #multiplelinearregression #regression #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics

How Artificial Intelligence, Machine Learning and Deep Learning integrate. . :: A lot of people ask me, what is this good for and how is Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) related to one another. I will start a new series of images explaining this, in baby steps, starting from a big picture and slowly going into details. This is the first post of that series of exploring AI, ML and DL in more detail. Yes, this is already a lot of detail as a start, but somewhere one needs to start I figured. . :: So, this first post could make a point about how AI, ML and DL are not to be looked at as different things, in fact, they rely on each other. AI is using methods of ML and DL to mimic human behaviour, like speaking (cortana by @Microsoft), or seeing (self-driving cars by @Tesla and many more). ML is a method using statistics, probably the earliest form of ML were expert systems. Finally, DL is one specific technique of ML, to be precise, neural networks and even further, multi-layered neural networks. . #artificialintelligence #machinelearning #deeplearning #ai #ml #dl #data #dataprocessing #datascience #datascientist #datavisualization #statistics #analytics #dataanalytics

@artificialintelligence.digest

Tags

Bjarne Stroustrup C# C++ Daniel Shiffman FLTK Game Dev GLPK Linear Programming Principles and Practice Using C++ Random Walk Rhinoceros Grasshopper The Nature of Code Unity

Blog at WordPress.com.

Post to

Cancel

%d bloggers like this: