You always start with the basics, and with AI it's no different! We'll be getting our feet wet with some simple, but powerful, models and demonstrate their power by applying them to real world data.
For our first paper in intelligence, we'll be covering how to detect hate speech using machine learning algorithms. This is a super interesting topic, because hate speech is often hard to define and depends a lot on the context surrounding it. This review paper will cover current state-of-the-art approaches for this problem.
We invite all of our members and those of you with topics they're passionate about to be a part of our Project Teams this semester! We will be hosting a fun, informal meeting where everyone is free to write down their interests and ideas, converse with other students, and form teams based on the topics pitched. Note: Not everyone's idea may make it through, but we encourage you to pitch ideas and by the end of the night each of you will be paired in a group based on those interests. Ideas will be narrowed down by coordinators who are facilitating this meeting, and the teams will be formed with a team leader who will manage and support the project throughout the semester. Some project teams will be continuing from last semester! Feel free to reach out and join one of our ongoing projects as well.
In this lecture, we explore powerful yet lightweight models that are often overlooked. We will see the power of combining multiple simple models together and how they can yield amazing results. You won't believe how easy it is to classify with just a line!
We invite all of our members and those of you with topics they're passionate about to be a part of our Project Teams this semester! We will be hosting a fun, informal meeting where everyone is free to write down their interests and ideas, converse with other students, and form teams based on the topics pitched. Note: Not everyone's idea may make it through, but we encourage you to pitch ideas and by the end of the night each of you will be paired in a group based on those interests. Ideas will be narrowed down by coordinators who are facilitating this meeting, and the teams will be formed with a team leader who will manage and support the project throughout the semester. Some project teams will be continuing from last semester! Feel free to reach out and join one of our ongoing projects as well.
Tonight we'll be encouraging you not to drink the KoolAid and work to demystify common terms surrounding Artificial Intelligence. Afterwards we'll have a Q/A (AMA) session where members can ask anything they want about the club and its leadership. During our Q/A you'll have the opportunity to vote up questions you want answered the most.
You've heard about them: Beating humans at all types of games, driving cars, and recommending your next Netflix series to watch, but what ARE neural networks? In this lecture, you'll actually learn step by step how neural networks function and learn. Then, you'll deploy one yourself!
This week we'll be discussing various ethical topics surrounding Artificial Intelligence. We'll be exploring popular and unpopular viewpoints, known and unknown champions of these views, and fear versus trust-based perspectives. This is the perfect opportunity for you all to come and voice your opinions or concerns about Ethics in Artificial Intelligence.
Ever wonder how Facebook tells you which friends to tag in your photos, or how Siri can even understand your request? In this meeting we'll dive into convolutional neural networks and give you all the tools to build smart systems such as these. Join us in learning how we can grant our computers the gifts of hearing and sight!
Many organisms can predict future events from the statistics of past experience, but humans also excel at making predictions by pure reasoning-- integrating multiple sources of information, guided by abstract knowledge, to form rational expectations about novel situations, never directly experienced. Here, we show that this reasoning is surprisingly rich, powerful, and coherent even in preverbal infants.
This lecture is all about Recurrent Neural Networks. These are networks with memory, which means they can learn from sequential data such as speech, text, videos, and more. Different types of RNNs and strategies for building them will also be covered. The project will be building a LSTM-RNN to generate new original scripts for the TV series "The Simpsons". Come and find out if our networks can become better writers for the show!
The ability to perform a detailed decision-making approach based on large quantities of parameters and data is at the core of the majority of sciences. Traditionally, all possible scenarios should be considered, and their outcomes assessed via a logical and systematic manner to obtain accurate and applicable methods for knowledge discovery. However, such approach is typically associated with high computational complexity. In this article we discuss some requirements of artificial intuition and present a model of artificial intuition that utilises semantic networks to improve a decision system.
It's time to put what you have learned into action. Here, we have prepared some datasets for you to build a a model to solve. This is different from past meetings, as it will be a full workshop. We provide the data sets and a notebook that gets you started, but it is up to you to build a model to solve the problem. So, what will you be doing? We have two datasets, one is using planetary data to predict if a planet is an exoplanet or not, so your model can help us find more Earth-like planets that could contain life! The second dataset will be used to build a model that mimics a pokedex! Well, not fully, but the goal is to predict the name of a pokemon and also predict its type (such as electric, fire, etc.) This will be extremely fun and give you a chance to apply what you have learned, with us here to help!
Piggybacking off our ethics discussion in this week's GBM, we'll be focusing on the ethical considerations surrounding use of artificial intelligence in therapeutic applications, specificially with respect to aiding current state of the art approaches to therapy. Much of the paper discusses surveys and statistics of physicians and their attitudes towards technology, and our discussion will extend this to address the ethical backdrop for the topics mentioned.
How can we infer on the past to predict the future? In this meeting we are going to be learning about time series data and its unique qualities. After we sharpen up our data science skills, we will be putting them to good use by analyzing and predicting the spread of the Coronavirus!
This week's paper will investigate a new approach for analyzing psychometric qualities from text. Psychometrics, such as emotions or personality traits, are often subconsciously conveyed through the manner in which people communicate. The authors of the paper propose a new method for analyzing psychometric qualities of authors using a modification of other previously developed architectures for natural language processing and analysis.
GANs are relativity new in the machine learning world, but they have proven to be a very powerful architecture. Recently, they made headlines in the DeepFake network, being able to mimic someone else in real time in both video and audio. There has also been cycleGAN, which takes one domain (horses) and makes it look like something similar (zebras). Come and learn the secret behind these type of networks, you will be surprised how intuitive it is! The lecture will cover the basics of GANs and different types, with the workshop covering how we can generate human faces, cats, dogs, and other cute creatures!
We all remember when DeepMind’s AlphaGo beat Lee Sedol, but what actually made the program powerful enough to outperform an international champion? In this lecture, we’ll dive into the mechanics of reinforcement learning and its applications.
We've learned about linear and statistical models as well as different training paradigms, but we've yet to think about how it all began. In Cognitive Computational Neuroscience, we look at AI and ML from the perspective of using them as tools to learn about human cognition, in the hopes of building better AI systems, but more importantly, in the hopes of better understanding ourselves.