Page 7 – iteration, making, building, and coding in education

Scaling up SBG for the New Year

In my new school, the mean size of my classes has doubled. The maximum size is now 22 students, a fact about which I am not complaining. I’ve missed the ease of getting students to interact with simple proximity as the major factor.

I have also been given the freedom to continue with the standards based grading system that I’ve used over the past four years. The reality of needing to adapt my systems of assessment to these larger sizes has required me to reflect upon which aspects of my system need to be scaled, and what (if anything) needs to change.

The end result of that reflection has identified these three elements that need to remain in my system:

Students need to be assessed frequently through quizzes relating to one to two standards maximum.
These quizzes need to be graded and returned within the class period to ensure a short feedback cycle.
There must still be a tie between work done preparing for a reassessment and signing up for one.

Including the first element requires planning ahead. If quizzes are going to take up fifteen to twenty minutes of a class block, the rest of the block needs to be appropriately planned to ensure a balance between activities that respond to student learning needs, encourage reinforcement of old concepts, and allow interaction with new material. The second element dictates that those activities need to provide me time to grade the quizzes and enter them as standards grades before returning them to students. The third happens a bit later in the cycle as students act on their individualized needs to reassess on individual standards.

The major realization this year has been a refined need for standards that can be assessed within a twenty minute block. In the past, I’ve believed that a quiz that hits one or two aspects of the topic is good enough, and that an end of unit assessment will allow complete assessment on the whole topic. Now I see that a standard that has needs to have one component assessed on a quiz, and another component assessed on a test, really should be broken up into multiple standards. This has also meant that single standard quizzes are the way to go. I gave one quiz this week that tested a previously assessed standard, and then also assessed two new ones. Given how frantic I was in assessing mastery levels on three standards, I won’t be doing that again.

The other part of this first element is the importance of writing efficiently targeted assessment questions. I need students to arrive at a right answer by applying their knowledge, not by accident or application of an algorithm. I need mistakes to be evidence of misunderstanding, not management of computational complexity. In short, I need assessment questions that assess what they are designed to assess. That takes time, but with my simplified schedule this year, I’m finding the time to do this important work.

My last post was about my excitement over using the Numbas web site to create and generate the quizzes. A major bottleneck in grading these quizzes quickly in the past has been not necessarily having answers to the questions I give. Numbas allows me to program and display calculated answers based on the randomized values used to generate the questions.

Numbas has a feature that allows students to take the exam entirely online and enter their answers to be graded automatically. In this situation, I have students pass in their work as well. While I like the speed this offers, that advantage primarily exists in cases where students answer questions correctly. If they make mistakes, I look at the written work and figure out what went wrong, and individual values require that I recalculate along the way. This isn’t a huge problem, but it brings into question the need for individualized values which are (as far as I know right now) the only option for the fully online assessment. The option I like more is the printed worksheet theme that allows generation of printable quizzes. I make four versions and pass these out, and then there are only four sets of answers to have to compare student work against.

With the answers, I can grade the quizzes and give feedback where needed on wrong answers in no more than ten or fifteen minutes total. This time is divided into short intervals throughout the class block while students are working individually. The lesson and class activities need to be designed to provide this time so I can focus on grading.

The third element is still under development, but my credit system from previous years is going to make an appearance. Construction is still underway on that one. Please pardon the dust.

P.S:

If you’re an ed-tech company that wants to impress me, make it easy for me to (a) generate different versions of good assessment questions with answers, (b) distribute those questions to students, (c) capture the student thinking and writing that goes with that question so that I can adjust my instruction accordingly, and (d) make it super easy to share that thinking in different ways.

That step of capturing student work is the roughest element of the UX experience of the four. At this time, nothing beats looking at a student’s paper for evidence of their thinking, and then deciding what comes next based on experience. Snapping a picture with a phone is the best I’ve got right now. Please don’t bring up using tablets and a stylus. We aren’t there yet.

Right now there are solutions that hit two or three, but I’m greedy. Let me know if you know about a tool that might be what I’m looking for.

Numbas and Randomized Assessment

At the beginning of my summer vacation, I shared the results of a project I had created to fill a need of mine to generate randomized questions. I subsequently got a link from Andrew Knauft (@aknauft) about another project called Numbas that had similar goals. The project is out of Newcastle University and the team is quite interested in getting more use and feedback on the site.

You can find out more at http://www.numbas.org.uk/. The actual question editor site is at https://numbas.mathcentre.ac.uk/.

I’ve used the site for a couple of weeks now for generating assessments for my students. I feel pretty comfortable saying that you should be using it too, and in place of my own QuestionBuilder solution. I’ve taken the site down and am putting time into developing my own questions on Numbas. Why am I so excited about it?

It has all of the randomization capabilities of my site, along with robust variable browsing and grouping, conditions for variable constraints, and error management in the interface that I put on the back burner for another day. Numbas has these features right now
LaTEX formatting is built in along with some great simplification functions for cleaning up polynomial expressions.
Paper and online versions (including SCORM modules that work with learning management sites like Moodle) are generated right out of the box.
It’s easy to create, share, and copy questions that others have created and adapt them to your own uses.
Visualization libraries, including Geogebra and Viz.js, are built in and ready to go.
The code is open sourced and available to install locally if you want to do so.

I have never planned to be a one-person software company. I will gladly take the output of a team of creative folks that know what they are doing with code over my own pride, particularly when I am energized and focused on what my classroom activities will look like tomorrow. The site makes it easy to generate assessments that I can use with my students with a minimal amount of friction in the process.

I’ll get more into the details of how I’ve been using Numbas shortly. Check out what they’ve put together – I’m sure you’ll find a way to include it in part of your workflow this year.

Context and Learning Names

I wrote yesterday about my decision to try learning names of my students on the first day.

As of the middle of week two, I’ve learned the names of every student within each class with few exceptions. In some of the bigger groups, I mix one or two names that start with the same first letter, but I correct myself pretty quickly. I’ve come to recognize some individual traits that make each student unique within the group, and am feeling comfortable building on my knowledge of their names to find out more about who they are.

In the hallways, in line for lunch, and walking around campus, I struggle. Outside of the classroom, I lack the context of those names that I can usually lean back upon to remember them. With the students all mixed up together, including with students that I don’t have in my classes, it takes longer to put a name with the face. As I develop an understanding of the students beyond names, this struggle will go away.

The analogy to learning in any classroom context stands on its own, so I won’t ruin it with more commentary.

Fail Early, Fail Often: Learning Names

Learning names this year was a bigger challenge this time around in comparison to the past few years. The first reason is that my new school is substantially bigger than my previous school, as are the class sizes. Another major reason: I’m the new guy.

The students generally know each other, so I decided the first day wasn’t actually about them learning each other’s names. I still included activities that got them interacting with each other, but I was the one that needed to learn their names. I decided the quick forty minute block on the first day was an opportunity to model my class credo: fail early, fail often.

When they walked in, I asked them their names, and what they wanted to be called. I’ve learned that these are not necessarily the same. These names were noted on my clipboard. I made a big show out of going around to each student, looking them in the eyes, and saying their name. Taking attendance then became my first opportunity to assess what I remembered. The order on the roster definitely didn’t match the order that the students entered the classroom.

I then had them line up alphabetically along the back wall. I had them all say their names one in a row. I had my reference material on the clipboard and went reverse alphabetical order. I publicly made mistakes, lots of them. Then I had them say the name of the person immediately to their left. For me learning the names, this meant that the voice saying the name was different, but the name was the same. I narrated that I wasn’t actually looking at the person saying the name – my attention was on the person whose name was being said.

I then had them get in line in order of birthday, but without any words. Once they figured out their order, I went down the line and tried to get names. I looked at my clipboard if I needed to, and I often did, but often had them just say their names back. I explained that I made them move around because I didn’t want to learn names based on who each person was next to – I needed to connect the name to the face. This ensured I was learning the right information, not an arbitrary order.

Then I had them get into two or three random orders. If there was time, I had a student go down the line reciting names. Then I went again myself, now trying not to look at the clipboard unless it was absolutely necessary. The mistakes continued to come, but I generally was having more success at this stage. I again told them that I had quizzes myself enough – it was time to let my brain do connecting behind the scenes. I emphasized that this was why cramming doesn’t tend to work: the brain is really good at organizing the information if it has the time to do so.

It was great putting myself in the position of not knowing answers and having to ask students for help. The students appeared to enjoy my genuine attempt to demonstrate how I learn information efficiently, and how essential failure is to being successful in the end.

Moving to Vietnam

After a whirlwind tour visiting family, friends, and taking care of many more errands than in a typical summer vacation, my family and I arrived in Vietnam mid-July. The 27 hours of travel went far more smoothly and quickly than expected. This was at least partly due to the fact that the under-filled coach cabin yielded our now eight-month old daughter her own seat.

All of this was a big step toward the next stage of my teaching career: I’ve joined the high school faculty at the Saigon South International School, located in District 7 of Ho Chi Minh City. This past week, I started my year teaching two sections of the first year of IB Mathematics SL, two sections of pre-Calculus, and a section of Algebra 2 & trigonometry. If you’ve heard me discuss my teaching load at my previous school, you’ll know that this is half the number of preps, and one more open block in my schedule than I’ve had for the past six years. I’ve been amazed by my colleagues and their range of international experiences, both in and out of my department. The energy to try new things and a drive to challenge my teaching practices are both part of the culture here, and it’s very exciting to be on this team for the new year.

I’ll continue to write on this blog, which has often played second fiddle to other obligations in the past couple of years. My hope is to reflect more regularly as part of an effort to do fewer things, but with greater focus. I hope you’ll continue to join me.

2015-2016 Year in Review: IB Mathematics SL/HL

This was my second year working in the IB program for mathematics. For those that don’t know, this is a two year program, culminating in an exam at the end of year two. The content of the standard level (SL) and higher level (HL) courses cross algebra, functions, trigonometry, vectors, calculus, statistics, and probability. The HL course goes more into depth in all of these topics, and includes an option that is assessed on a third, one-hour exam paper after the first two parts of the exam.

An individualized mathematics exploration serves as an internally assessed component of the final grade. This began with two blocks at the end of year one so that students could work on it over the summer. Students then had four class blocks spread out over the first month of school of year two two work and ask questions related to the exploration during class.

I taught year one again, as well as my first attempt at year two. As I have written about previously, this was run as a combined block of both SL and HL students together, with two out of every five blocks as HL focused classes.

What worked:

I was able to streamline the year 1 course to better meet the needs of the students. Most of my ability in doing this came from knowing the scope of the entire course. Certain topics didn’t need to be emphasized as I had emphasized in my first attempt last year. It also helped that the students were much better aware of the demands of higher-level vs. standard level from day one.
I did a lot more work using IB questions both in class and on assessments. I’ve become more experienced with the style and expectations of the questions and was better able to speak to questions about those from students.
The two blocks on HL in this combined class was really useful from the beginning of year one, and continued to be an important tool for year two. I don’t know how I would have done this otherwise.
I spent more time in HL on induction than last year, both on sums and series and on divisibility rules, and the extra practice seemed to stick better than it did last year in year one.
For students that were self starters, my internal assessment (IA) schedule worked well. The official draft submitted for feedback was turned in before a break so that I had time to go through them. Seeing student’s writing was quite instructive in knowing what they did and did not understand.
I made time for open ended, “what-if” situations that mathematics could be used to analyze and predict. I usually have a lot of this in my courses anyway, but I did a number of activities in year one specifically to hint at the exploration and what it was all about. I’m confident that students finished the year having seen me model this process, and having gone through mini explorations themselves.
After student feedback in the HL course, I gave many more HL level questions for practice throughout the year. There was a major disconnect between the textbook level questions and what students saw on the HL assessments, which were usually composed of past exam questions. Students were more comfortable floundering for a bit before mapping a path to a solution to each problem.
For year two, the exam review was nothing more than extended class time for students to work past papers. I did some curation of question collections around specific topics as students requested, but nearly every student had different needs. The best way to address this was to float between students as needed rather than do a review of individual topics from start to finish.
The SL students in year two learned modeling and regression over the Chinese new year break. This worked really well.
Students that had marginally more experience doing probability and statistics in previous courses (AP stats in particular) rocked the conditional probability, normal distribution, and distribution characteristics. This applied even to students who were exposed to that material, but did poorly on it in those courses. This is definitely a nod to the idea that earlier exposure (not mastery) of some concepts is useful later on.
Furthermore, regarding distributions, my handwaving to students about finding area under the curve using the calculator didn’t seem to hurt the approach later on when we did integration by hand.
This is no surprise, but being self sufficient and persevering through difficult mathematics needs to be a requirement for being in HL mathematics. Students that are sharp, but refuse to put in the effort, will be stuck in the 1-3 score range throughout. A level of algebraic and conceptual fluency is assumed for this course, and struggling with those aspects in year one is a sign of bigger issues later on. Many of the students I advised this way in year one were happier and more successful throughout the second year.
I successfully had students smiling at the Section B questions on the IB exam in the slick way that the parts are all connected to each other.

What needs work:

For year one:

I lean far too hard on computer based solutions (Geogebra, Desmos) than on the graphing calculator during class. The ease of doing it these ways leads to students being unsure of how to use the graphing calculator to do the same tasks (finding intersections and solutions numerically) during an assessment. I definitely need to emphasize the calculator as a diagnostic tool before really digging into a problem to know whether an integer or algebraic solution is possible.
Understanding the IB rounding rules needs to be something we discuss throughout. I did more of this in year one on my second attempt, but it still didn’t seem to be enough.

For year two:

Writing about mathematics needs to be part of the courses leading up to IB. Students liked the mini explorations (mentioned above) but really hated the writing part. I’m sure some of this is because students haven’t caught the writing bug. Writing is one of those things that improves by doing more of it with feedback though, so I need to do much more of this in the future.
I hate to say it, but the engagement grade of the IA isn’t big enough to compel me to encourage students to do work that mattered to them. This element of the exploration was what made many students struggle to find a topic within their interests. I think engagement needs to be broadened in my presentation of the IA to something bigger: find something that compels you to puzzle (and then un-puzzle) yourself. A topic that has a low floor, high ceiling serves much more effectively than picking an area of interest, and then finding the math within it. Sounds a lot like the arguments against real world math, no?
I taught the Calculus option topics of the HL course interspersed with the core material, and this may have been a mistake. Part of my reason for doing this was that the topic seemed to most easily fit in the context of a combined SL/HL situation. Some of the option topics like continuity and differentiability I taught alongside the definition of the derivative, which is in the core content for both SL and HL. The reason I regret this decision is that the HL students didn’t know which topics were part of the option, which appear only on a third exam section, Paper 3. Studying was consequently difficult.
If for no other reason, the reason not to do a combined SL/HL course is that neither HL or SL students get the time they deserve. There is much more potential for great explorations and inquiry in SL, and much more depth that is required for success in HL. There is too much in that course to be able to do both courses justice and meet the needs of the students. That said, I would have gone to three HL classes per two week rotation for the second semester, rather than the two that I used throughout year one.
The HL students in year two were assigned series convergence tests. The option book we used (Haese and Harris) had some great development of these topics, and full worked solutions in the back. This ended up being a miserable failure due to the difficulty of the content and the challenge of pushing second semester seniors to work independently during a vacation. We made up some of this through a weekend session, but I don’t like to depend on out-of-school instruction time to get through material.

Overall, I think the SL course is a very reasonable exercise in developing mathematical thinking over two years. The HL course is an exercise in speed and fluency. Even highly motivated students of mathematics might be more satisfied with the SL course if they are not driven to meet the demands of HL. I also think that HL students must enjoy being puzzled and should be prepared to use tricks from their preceding years of mathematics education outside of being taught to do so by teachers.

QuestionBuilder: Create and Share Randomized Questions

I’ve written previously about my desire to write randomized questions for the purpose of assessment. The goal was never to make a worksheet generator – those exist on the web already. Instead, I wanted to make it easy to create assessment questions that are similar in form, but different enough from each other that the answers or procedures to solve them are not necessarily identical.

Since January, I’ve been working on a project called QuestionBuilder. It’s a web application that does the following:

Allows the creation of assessment questions that contain randomized elements, values, and structures.
Uses regular Javascript, HTML, and the KaTEX math rendering library to create and display the questions
Makes it easy to share questions you create with community members and build upon the work of others to make questions that work for you.

Here’s a video in which I convert a question from the June 2016 New York State Regents exam for Algebra 2 Common Core into a randomized question. Without all of my talking, this is a quick process.

I’ve put a number of questions on the site already to demonstrate what I’ve been using this to do. These range from simple algebra to physics questions. Some other folks I appreciate and respect have also added questions in their spare time.

For now, you’ll need to create an account and log in to see these questions in action. Go to http://question-builder.evanweinberg.org, make an account, and check out the project as it exists at this point.

My hope is to use some time this summer to continue working on it to make it more useful for the fall. I’ll also be making some other videos to show how to use the features I’ve added thus far. Feel free to contact me here, through Twitter (@emwdx), or by email (evan at evanweinberg.com) if you have questions or suggestions.

Generality vs. Specificity

We want our students to have problem solving methods that are general enough to work in any situation. If we assign a series of exercises that are too similar to each other, it becomes easy for students to lock onto the wrong pattern, or to use a ‘trick’ that works just frequently enough to seem worth the effort to learn it.

One thing I tried this year was to prompt students to make themselves aware of the spectrum from generality to specificity. What works for solving specifically this question? What general ideas apply to answering all of the problems on the page?

I used my randomized question generator to help create problems that worked this way. Here’s an example:

I only started a deliberate effort to prompt these conversations at the middle of the second semester. I wish I was doing it all year.

Endings and Beginnings

Today, I bid farewell to my home away from home for the past six years.

When I first moved away from New York, I had shed all doubts that the teaching career was for me. I knew that learning and exploring were important elements of a meaningful existence on this planet, both for me and my students. I knew that few things were more satisfying than spending time with good people around plates of food. I knew that not knowing the local language or the location of the nearest supermarket was a cause for excitement, not fear. Purposely putting one’s self into situations with unknown outcomes is not a reckless act. It is precisely these challenges that define and refine who we are so that we are better prepared for those events that we do not expect.

I knew these things already. And yet, I leave China today as a changed teacher. I met students from all around the world. I made connections not just with new people in the same building as me, but with teachers in many distributed time zones. People that I respected and admired for their ideas humbled me as they invited me to join in their conversations and explore ideas with me. I found opportunities to present at conferences and get to know others that had also fallen in love with the international teaching lifestyle. I started this blog, and surprisingly, had people read it with thoughts of their own to share.

I also learned to accept the reality that life continues in twenty four time zones. News from home made it seem more foreign and paradoxically more connected to my own experiences here. When opening my eyes and my various devices in the morning to see what had happened while I slept, I again never knew what to expect. I lost family members both suddenly and over stretches of time. Kids grew up. Our parents sold their houses and apartments. Friends put prestigious letters at the end of their names.

Our world changed as well. We added new countries to our passports and got lost in cities that refused to abide by a grid system. We fell in love with our dog and his aggressive sneezing at harmless bystanders. We tried to address the life and work balance through weeknight dinners and mini vacations. We repeatedly overcommitted to traveling during our summers off and time went too quickly. We became parents.

I write this not because anything I’m saying is especially new. The ‘time marches on’ canon is well established. That does not invalidate the reality that we’re all experiencing life and its passage for the first time ourselves. This is the magic that we, as teachers, witness between the end of one year and the beginning of the next. We tweak our lessons from the previous year with the hope that they prompt more questions and productive confusion on the next iteration. Our students do experience some of the ideas we introduce for the first time in our classrooms, and it is unique that we get to design those experiences ourselves.

The best way to understand the rich range of emotions that our students experience while in our care is to live deeply and richly in our own lives. We need to learn to know and love others, explore and make mistakes, and be ready to move forward even when the future is uncertain. My time abroad thus far has given me numerous journeys through these human experiences. I would not give them up for the world, and luckily, I do not have to do so.

I’ll write more about my next move in a future post.
Until then, I wish you all a summer full of good times with good people.

Hacking the 100-point Scale – Part 4: Playing with Neural Networks

First, a review of where we’ve been in the series:

The 100 point scale suffers from issues related to its historical use and difficulties of communicating what it means.
It might be beneficial to have a solid link between the 100 point scale (since it likely isn’t going anywhere) and the idea of achievement levels. This does not need to be rigidly defined as 90 – 100 = A, 80-89 = B, and so on.
I asked for you to help me collect some data. I gave you a made up rubric with three categories, and three descriptors for each, and asked you to categorize these as achievement levels 1 – 4. Thank you to everyone who participated!

This brings us to today’s post, where I try to bring these ideas together.

In case you only have time for a quick overview, here’s the tl;dr:

I fed the rubric scores you all sent me after the previous post to train a neural network. I then used that neural network to grade all possible rubric scores and generate achievement levels of 1, 2, 3, or 4.

Scroll down to the image to see the results.

Now to the meat of the matter.

Rubric design is not easy. It takes quite a bit of careful thought to decide on descriptors, point values and much of the time we don’t have a team of experts on the payroll to do this for us.

On the other hand, we’re asked to make judgements on students all the time. These judgements are difficult and subjective at times. Mathematical tools like averages help reduce the workload, but they do this at the expense of reducing the information available.

The data you all gave me was the result of educational judgment, and that judgement comes from what you prioritize. In the final step of my Desmos activity, I asked what you typically use to relate a rubric score to a numerical grade. Here are some of the responses.

From @aknauft:

I need to see a consistent pattern of top rubric scores before I assign the top numerical grade. Similarly, if the student does *not* have a consistent set of low rubric scores, I will *not* give them the low numerical grade.
Here specifically, I was looking for:
3 scores of 1 –> skill level 1
2 scores of 2 or 1 score of 3 –> skill level 2 or more
2 scores of 3 –> skill level 3 or more
3 scores of 3 –> skill level 4

From Will:

Sum ‘points’
3 or 4 points= 1
5 or 6 points = 2
7 points= 3
8 or 9 points = 4

From Clara:

1 is 60-70
2 is 70-80
3 is 80-90
4 is 90-100
However, 4 is not achievable based on your image.
Also to finely split each point into 10 gradients feels too subjective.
Equivalency to 100 (proportion) would leave everyone except those scoring 3 on the 4 or scale, failing.

Participant Paul also shared some helpful percentages that directly relate the 1 – 4 scale to percentages, perhaps off of his school’s grading policy. I’d love to know more. Dennis (on the previous post) commented that multi-component analysis should be done to set the relative weights of the different categories. I agree with his point that this is important and that it can easily be done in a spreadsheet. The difficulty is setting the weights.

The experience of assigning grades using percentages is a time saver, and is easy because of its historical use. Generating the scales as the contributors above did is helpful for relating how a student did on a task to their level. My suggestion is that the percentages we use for achievement levels should be an output of the rubric design process, not an input. In other words, we’ve got it all backwards.

I used the data you all gave me and fed it into a neural network. This is a way of teaching a computer to make decisions based on a set of example data. I wanted the network to understand how you all thought a particular set of rubric scores would relate to achievement level, and then see how the network would then score a different set of rubric scores.

Based solely on the six example grades I asked you to give, here are the achievement levels the neural network spit out:

I was impressed with how the network scored with the twenty one (out of 27 possible permutations) that you didn’t score. It might not be perfect, and you might not agree with every one. The amazing part of this process, however, is that any results you disagree with could be tagged with the score you prefer, and then the network could retrain on that additional training data. You (or a department of teachers) could go through this process and train your own rubric fairly quickly.

I was also curious about the sums of the scores that led to a given achievement level. This is after all what we usually do with these rubrics and record in the grade book. I graphed the rounded results in Desmos. Achievement level is on the vertical axis, and sum is on the horizontal.

One thing that struck me is the fuzziness around certain sum values. A score of 6, for example, leads to a 1, 2, or a 3. I thought there might be some clear sum values that might serve as good thresholds for the different levels, but this isn’t the case. This means that simply taking the percentage of points earned and scaling into the ten point ranges for A, B, C, and D removes some important information about what a student actually did on the rubric.

A better way to translate these rubric scores might be to simply give numerical grades that indicate the levels, and communicate the levels that way as part of the score in the grade book. “A score of 75 indicates the student was a level 2.”

Where do we go from here? I’m not sure. I’m not advocating that a computer do our grading for us. Along the lines of many of my posts here, I think the computer can help alleviate some of the busy work and increase our efficiency. We’re the ones saying what’s important. I did another data set where I went through the same process, but acted like the third category was less important than the other two. Here’s the result of using that modified training data:

It’s interesting how this changed the results, but I haven’t dug into them very deeply.

I just know that something needs to change. I had students come to me after final exam grades were put in last week (which, by the way, were raw percentage grades) and being confused by what their grades meant. The floor for failing grades is a 50, and some students interpreted this to mean that they started with a 50, and then any additional points they earned were added on to that grade. I use the 50 as a floor, meaning that a 30% raw score is listed as a 50% in the final exam grade. We need to improve our communication, and there’s a lot of work to do if the scale isn’t going away.

I’m interested in the idea of a page that would let you train any rubric of any size through a series of clicks. What thoughts do you have at the end of this exploration?

Technical Details:

I used the Javascript implementation of a neural network here to do the training. The visualizations were all made using the Raphael JS library.

« Prev 1 … 5 6 7 8 9 … 32 Next »