What I Learned from the O'Reilly AI Conference Keynotes
Earlier this week, I attended the O'Reilly AI Conference up in San Jose, CA. Wednesday and Thursday started off with keynotes showcasing what companies were currently researching in the field of AI. While I'm no expert in the field, I found four key takeaways from the keynotes.
Bejeweled 1 AI (Part 3): Creating a Smarter AI
In part 1, I used OpenCV and Python to load our game and get to the board data. In part 2, I built the basic mechanics for our AI to make moves.
In this post, I'll be going over more advanced mechanisms used to allow our AI to make better moves.
Bejeweled 1 AI (Part 2): Enabling AI to Make Moves
In my previous post, I was able to get our code to get past the loading screen and get the board information. However, a program that can only grab the board without acting on the information does no good. In this post, we'll be adding the basic mechanisms for our AI to act on the board information. Please note that more intelligent behavior won't be added in this post.
An Introduction to Chatbots
With the rise of Siri, Google Home, Alexa, and Cortana, it's obvious that there's a demand for chatbots. In the past, chatbots were more of a niche technology due to limited functionality. With recent advancements in computer technology, chatbots have now become practical for everyday use.
What is a Chatbot?
First, let’s define the term “chatbot.” What exactly is a chatbot?
Think of it like a customer support representative. You contact support, they ask about the problem, you describe them the problem you’re having, they ask further questions to pinpoint the problem, and eventually you get a solution.
Now, replace the person with a computer program, the program being an on-demand Q&A application. That is a chatbot.
Types of Chatbot
Designing chatbots can be quite complex since you’re dealing with intensive computing power, immense datasets, and ambiguity of natural language. However, we can derive two main types of chatbots.
Rule-based Chatbot
In rule-based, a chatbot answer questions based on a series of rules. These rules are predefined by the developer and depending on the user’s actions, would trigger other rules.
Rule-based makes developing chatbots simpler as you only need to work in a very limited context. However, this simplicity also prevent chatbots from getting smarter.
Take the image below as an example.
In the image, our chatbot is geared towards helping users shop on an e-commerce website. When the user go to the chatbot, the bot will first greet the user. Usually this is a simple "hello."
While the options aren't limited to the ones shown above, the user can ask to place items into their shopping cart, determine whether an item is in stock, and understanding the refund policy.
Once the user types in a command, the chatbot will perform various actions depending on the task. The heavy lifting is done in the background and will notify the user once the action has completed. The user can either follow up with additional commands or just end the conversation.
However, the chatbot cannot handle tasks outside its domain like tracking items for delivery or buying tickets for the movie theater near you.
AI-based
With AI chatbots, you utilize a machine learning model to train your chatbot to handle user input. Oftentimes, chatbots utilize Deep Learning to derive a model. Additionally, you can tack on voice to text recognition to provide ease of communication to the user.
Unlike rule-based, you only supply training data to the model and the model will be tailored to the dataset. This flexibility allows the chatbot to handle complex sentences. However, since using Deep Learning is complex, it's harder to fine-tune the model. Additionally, utilizing it can be overkill for chatbots that work in simple environments.
Why the resurgence?
Simply put, we have three things that are going for us today:
- Computing power - While there were extensive theory on AI methods in the mid-20th century, the amount of computing power wasn't sufficient. Due to Moore's Law, we have been able to quickly and dramatically speed up processing power.
- Huge datasets - In the past, there wasn't a lot of data to be had for training and utilizing AI models. With the rise of the internet and complex system architectures need to handle petabytes of data, we know have access to an abundant amount of data.
- Resurgence of AI - In early days for AI research, people were overhyping the practicality of AI. As a result, an AI winter occurred in the 1980s and 1990s. During this time, there wasn't much research going on due to reduced funding. However, with the addition of the former two points, AI became more practical for everyday products and solutions. Whether we will hit another AI winter is up for debate, but there's definitely much research going at the moment.
Conclusion
While we haven't seen general AI, we have definitely seen more powerful chatbots taking hold in our daily lives. In fact, you can find many blog posts on how to build your own chatbot. It wouldn't be surprising if chatbots became very human-like in a few years. Now, whether or not you'll talk to chatbots more than humans is a discussion for another day.