Search for: All records

Neuron Sandbox is a browser-based tool that helps middle school students grasp basic principles of neural computation. It simulates a linear threshold unit applied to binary decision problems, which students solve by adjusting the unit's threshold and/or weights. Although Neuron Sandbox provides extensive visualization aids, solving these problems is challenging for students who have not yet been exposed to algebra. We collected survey, video, and worksheet data from 21 seventh grade students in two sections of an AI elective, taught by the same teacher, that used Neuron Sandbox. We present a scaffolding strategy that proved effective at guiding these students to achieve mastery of these problems. While the amount of scaffolding required was more than we originally anticipated, by the end of the exercise students understood the computation that linear threshold units perform and were able to generalize their understanding of the worksheet’s solve for threshold strategy to also solve for weights. 

The planetary model of the atom is alive and well in middle school science class—and in popular iconography—despite most educated adults’ awareness of its shortcomings. The model persists because it is easily visualized, intuitively understandable, and expresses important truths. Models don’t have to get everything right to be useful. Middle schoolers would be overwhelmed by a more correct description of electron orbitals as probability densities satisfying the Schrödinger equation. Better to just show orbitals as ellipses. In the current era, when immensely powerful AI technologies built on neural networks are rapidly disrupting the world, K-12 students need age-appropriate models of neural networks just as they need age-appropriate models of atoms. We suggest the linear threshold unit as the best model for introducing middle school students to neural computation, and we present an interactive tool, Neuron Sandbox, that facilitates their learning. 

Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing. In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word prediction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., "king" minus "man" plus "woman" equals "queen". To help novices appreciate this idea, people have sought effective graphical representations of word embeddings.We describe a new interactive tool for visually exploring word embeddings. Our tool allows users to define semantic dimensions by specifying opposed word pairs, e.g., gender is defined by pairs such as boy/girl and father/mother, and age by pairs such as father/son and mother/daughter. Words are plotted as points in a zoomable and rotatable 3D space, where the third ”residual” dimension encodes distance from the hyperplane defined by all the opposed word vectors with age and gender subtracted out. Our tool allows users to visualize vector analogies, drawing the vector from “king” to “man” and a parallel vector from “woman” to “king-man+woman”, which is closest to “queen”. Visually browsing the embedding space and experimenting with this tool can make word embeddings more intuitive. We include a series of experiments teachers can use to help K-12 students appreciate the strengths and limitations of this representation. 

Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing. In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word prediction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., "king" minus "man" plus "woman" equals "queen". To help novices appreciate this idea, people have sought effective graphical representations of word embeddings.We describe a new interactive tool for visually exploring word embeddings. Our tool allows users to define semantic dimensions by specifying opposed word pairs, e.g., gender is defined by pairs such as boy/girl and father/mother, and age by pairs such as father/son and mother/daughter. Words are plotted as points in a zoomable and rotatable 3D space, where the third ”residual” dimension encodes distance from the hyperplane defined by all the opposed word vectors with age and gender subtracted out. Our tool allows users to visualize vector analogies, drawing the vector from “king” to “man” and a parallel vector from “woman” to “king-man+woman”, which is closest to “queen”. Visually browsing the embedding space and experimenting with this tool can make word embeddings more intuitive. We include a series of experiments teachers can use to help K-12 students appreciate the strengths and limitations of this representation.