Building an AI chatbot (part 1)

By
I am currently working on a personal assistant AI chatbot.

https://github.com/luweizhang/ai-buddy-node

Architecture:

  • wit.ai
  • Node.js (backend request hander)
  • Python Flask (backend ai layer - TensorFlow, Keras, NLTK)
  • PostgreSQL
  • Hosted on Heroku
For the chatbot, I will be using a retrieval based system.   I will have a database of possible responses.  A neural network will be trained to output the right response.  The inputs into the neural network will be the conversation context, user context, and the user response, the output will be the chat bot response.  

 Conversation context: history of the conversation
User context: information about the user
User response: most recent response from the user

 Here's a rough outline of the steps that need to be taken in order to build this AI.

 Step 1: 
Set up a server on Heroku.  

Step 2:
Setup up page on Facebook and tie into webhook

Step 3:
Set up PostgreSQL database, and populate with possible responses

Step 4:
Train model to predict responses. (either use a retrieval based model or generative model like an LSTM)

Step 5:
Set up wit.ai

Step 6:
????

Step 7:
$$$


alt text
a cool diagram outlining how this could work

Comments

Post a Comment

Popular posts from this blog

grandmaster level chess AI using python - Part 2 (the code)

By
Image
In continuation of part 1, I will now building my chess AI in python.  As mentioned before, my goal is to create a chess AI at the Grandmaster level (elo > 2500) Here is the code for the chess AI. https://github.com/luweizhang/chess_ai Key components of the chess game / AI: Python Classes: ChessGame instantiates the chessboard and pieces keeps track of whose turn it is RulesEnforcer Logic for how all the pieces move, castling Makes sure you cant make illegal moves Used in the chess AI to generation possible positions ChessAi Tree generator generates the tree of position moves Position Evaluator evaluates the quality of chess positions Minimax Determines the optimum move from the chess tree ChessDB Opening database Explanation of the tree generator: The tree generator component of the chess AI generates the possible future board positions based on the possible moves that the pieces can make.  At any given position, there are o...
Read more

building a chess ai - part 4: learning an evaluation function using deep learning (keras)

By
Image
Note: this post is still in progress. Below I will discuss approaches for training a deep learning chess game and the results of my implementation. Approach 1: Train against the outcome of the game *y* is the outcome of the game (1 is win for white, 0 is loss for white, .5 is draw) We want to learn a function * f(p)* that can approximate this. *p*  is the chess position (8x8 chess board), actually is an 8x8x12 = 768 dimensional vector (since there are 12 pieces)      8x8x6  = 384 dimensional vector with positive values for squares with a white piece and negative values for squares with a black piece.  (Using 64 x 12 introduces too many degrees of freedom) The goal is to try to learn a function * f(p)* that can predict the winner of the game * y* given a chess position * p* . The model: Dataset: http://www.ficsgames.org/download.html millions of high quality games played by grand masters or international masters Objective/Loss Function...
Read more

Brief intro to recurrent neural networks

By
Image
Note: This post is meant to be a brief and intuitive summary of recurrent neural networks.   I have adapted this material from the Coursera deep learning course.  The value I hope to add here is that I have attempted to summarize the information in a way that is easy (hopefully) to understand, and can be used as reference or refresher material for the future. Part 1: Recurrent Neural Networks: Recurrent neural networks are a class of neural networks where the nodes/neurons form a directed graph along a sequence.  They are very effective at tasks such as Natural Language Processing because they have a "memory," in other words they can receive context from previous inputs.  They can take in input one at a time, and can pass information from one node to the next via hidden activation layers.  This information serves as the "memory" or "context" layer of the network, which can be used in conjunction as more new input is being processed. RNN Cell: ...
Read more