Leveraging the Present to Anticipate the Future in VideosPredict future action labels instead of predicting pixel level information — Summarization of research paper…
Continue Readingaction
How to set up hypotheses
I learned nothing that changes my mind, let’s go out!Scenario 2 — You show me data: “Scientists just discovered a new kind…
Continue ReadingReinforcement Learning — Solving Blackjack
Reinforcement Learning — Solving BlackjackJeremy zhangBlockedUnblockFollowFollowingJun 14We have talked about how to use Monte Carlo methods to evaluate a policy in reinforcement…
Continue ReadingHow to Use Storytelling Conventions to Create Better Visualizations
Minor annoyances or moderately-challenging setbacks might lead her to make adjustments, but that doesn’t make for a compelling story. What…
Continue ReadingAction Movies vs Dramas: How do Their Scripts Differ?
Action Movies vs Dramas: How do Their Scripts Differ?An analysis of the differences between action movies and dramas using Python and…
Continue ReadingReinforcement Learning — Multi-Arm Bandit Implementation
Reinforcement Learning — Multi-Arm Bandit ImplementationJeremy zhangBlockedUnblockFollowFollowingMay 25Multi-Arm Bandit is a classic reinforcement learning problem, in which a player is facing with…
Continue ReadingAsynchronous with Redux Sagas
Asynchronous with Redux SagasSophisticated Side Effect Flow Management and TestingJolene LanglinaisBlockedUnblockFollowFollowingMay 28Building an app with React can get a bit confusing when…
Continue ReadingReact-Redux with TypeScript
Just to keep it simple, we’ll build the infamous to-do list application. Remember that the purpose is to understand how…
Continue ReadingOpen Minded AI: Improving Performance by Keeping All Options on the Table
If such a change will suddenly prevent us from taking action 2, then action X becomes the wrong decision. But…
Continue ReadingNever start with a hypothesis
Never start with a hypothesisLies, damned lies, and STAT101Cassie KozyrkovBlockedUnblockFollowFollowingNov 30, 2018Setting up hypothesis testing is a ballroom dance; its steps…
Continue ReadingCreating AI for GameBoy Part 4: Q-Learning and Variations
This is where the real magic happens — we’ve built our tools and now it is time to set them in motion.…
Continue ReadingSimple Reinforcement Learning: Q-learning
Simple Reinforcement Learning: Q-learningAndre ViolanteBlockedUnblockFollowFollowingMar 18Typical Exploring Image for RL – Credit @mike. shotsIntroductionOne of my favorite algorithms that I…
Continue ReadingHandling Redux Side-Effects — the RxJS way
If you are working with Redux you are probably walked into the same issue we had at Orfium FrontEnd team…
Continue ReadingTraining Bots to Play Tennis
Training Bots to Play TennisDeep Reinforcement Learning for Multi-Agent Collaboration & CompetitionThomas TraceyBlockedUnblockFollowFollowingFeb 22Photo credit: Ulf HoffmannThis post explores my work on…
Continue ReadingWhat’s coming to Rails 6.0?
What’s coming to Rails 6. 0?Guy MaliarBlockedUnblockFollowFollowingFeb 13Rails 6. 0 will be released soon and it’s packed with many features that…
Continue ReadingThe Other Type of Machine Learning
The Other Type of Machine LearningA brief introduction to Reinforcement LearningGenevieve HayesBlockedUnblockFollowFollowingFeb 9This is the first in a series of articles…
Continue ReadingHow to Understand Reducers: You Can Use Them Without Redux
What is a Reducer?Reducers are functions that take input and decide what to do it with it in one central spot.…
Continue ReadingThe most important idea in statistics
If the politics of your space exploration company elect the YES button as the right one to press under new…
Continue ReadingUser Segmentation and Power User Analysis in SQL
What actions do you look for?Power Users Bring You the Most ValueAs a consultant working with different clients, I run into…
Continue ReadingUsing Action Cable for Private Messaging & Presence Indicators on React/Rails app
Using Action Cable for Private Messaging & Presence Indicators on React/Rails appAlberto CarrerasBlockedUnblockFollowFollowingJan 10This article builds on Dakota Lillie’s great…
Continue ReadingUsing Action Cable With React
Now whenever the server sends data about a conversation to the client, it’ll only include the id and title fields…
Continue ReadingQrash Course: Deep Q Networks from the Ground Up in 10 Minutes
Qrash Course: Deep Q Networks from the Ground Up in 10 MinutesShaked ZychlinskiBlockedUnblockFollowFollowingJan 9This article assumes no prior knowledge in Reinforcement…
Continue ReadingDeep Reinforcement Learning for News Recommendation. Part 1: Architecture.
The input of the Critic network is the user state s generated by the user state representation module and the…
Continue ReadingReinforcement Learning from Scratch: Designing and Solving a Task All Within a Python Notebook
Those directly north, east, south of west can move in multiple directions whereas the states (1,1), (1,-1),(-1,-1) and (-1,1) can…
Continue ReadingKeeping your Laravel applications DRY with single action classes
We could put this code into the action itself, but we could also use a decorator pattern.Then, using Laravel’s IoC…
Continue Reading