You can also flip through images, edit them, and watch how changes propagate through the network in real time. It’s not in the public release yet (it's coming in a few weeks), but you can try it now on GitHub. See www.simbrain.net
Deep networks are complicated objects and showing them in an intuitive way presented many challenges, most of which we’ve overcome. You can view slices of tensors. You can “scroll” through the filters in a convolutional layer. If you hover over a pixel, all the patches that influence it light up.
A pigeon goes in, a classification comes out! #Simbrain now supports deep networks and CNNs. As activity propagates through the network, progressively more abstract features are formed, culminating in a representation sufficient for classification in the final layer.
Here’s a link to the paper that caught their attention, where I lay out my “metaphysical neutrality” thesis: link.springer.com/article/10.1...
Lots of other stuff came up along the way. I talked about how I got into philosophy, my journey from community college to the professoriate, what phenomenology is, epistemic humility, what neural networks tell us about the brain, and doing philosophy on tiktok.
I “bracket” the mind-body problem, so I rarely end up talking about it. But the hosts encouraged me to get into the details. They lean towards Kastrupian idealism, which is fairly new to me, and so it was a nice opportunity to have an open discussion and learn a few new things.
I was recently on the podcast “Reality Gone Mental”:
youtu.be/vk1K9x-qGOU
It was a refreshingly exploratory discussion. My take on the mind-body problem is that it can’t be solved so we should focus on the more tractable project of neurophenomenology... 1/
For more on Føllesdal’s life and work and the school of thought he helped give rise to, see this paper
jeffyoshimi.net/downloads/Ca...
Some relevant passages attached. The last two are quotes from Føllesdal himself, which highlight his willingness to depart from Husserl when necessary.
Dagfinn Føllesdal passed last week at the age of 93. He was my philosophical grandfather (my advisor's advisor), and was known as a founder of the “California School” of phenomenology. Here he is with his students David Smith and Ron McIntyre, as well as David’s students: Phil Walsh and myself.
If you have a project you are interested in or there is something you’d like to study or teach using this interface, feel free to message me.
Progress is happening rapidly. We are developing a full framework for processing tensors and building convolutional networks. This should be ready in weeks to months. Stay tuned!
The video at www.simbrain.net shows some of the main new features. The attached pictures show: a chaotic attractor, a simple retina reacting to a flower input, and part of a transformer model.
A full discussion of what’s new in Simbrain 4 is at docs.simbrain.net/docs/whatsnew
Over 50 complete simulations are included with documentation, covering evolved networks, backprop, language, vision, computational neuroscience, and vision, some of them battle tested with hundreds of students, some of the new and still being developed.
I’m thrilled to announce the release of #Simbrain 4, which I have been working on for over 10 years! For the last five of those years I have met almost every weeknight with Yulin Li and we have pair-programmed our way through the entire app, adding hundreds of new features.
I said a few words of remembrance about my "philosophical grandfather" Føllesdal here, and hope to write more soon
www.tiktok.com/@jeffyoshimi...
As for a single necessary and sufficient component for consciousness, I tend to treat cs as sui generis, rather than being defined by some essential property.
The answer is basically "I don't know". If all three are completely abolished, we think something like a "transcendental ego" remains, but then the question is whether that can be abolished. Possibly, but it's very hard to think about. See footnote 7.
Great questions! More later I have a long day ahead
My paper on the topic with Jason Ford just came out in a special issue on “Structuralism in the Science of Consciousness”. We develop a variational method to study the parts of experience, and use this method to describe a minimal form of self-consciousness.
Consciousness is not a sequence of isolated qualia, but a rich and structured field, with many interacting parts. These “parts” are like members of a symphony, whose contributions are distinctive but interwoven.
Tumors as rogue societies. academic.oup.com/emph/advance...
Do you include talks where you are a coauthor but did not attend the conference on your cv? I don't, but am curious what others do.
@tonyakubo.bsky.social
Fundraising and cancer walks are important, but we can do more: gamers, programmers, storytellers, and others can contribute their unique skills to building new kinds of games, which could lead to new discoveries.
Check it out here: www.tonyakubo.com/016-gaming-c...
I was recently on Tonya Kubo’s podcast, discussing the history of citizen science, what makes games so powerful and engaging, and how playing and building new scientific discovery games can be a way to channel grief towards collective action.
I am drawing on Thomas Sheehan’s and Richard E Palmer’s meticulously edited and thoroughly enjoyable volume on the Husserl-Heidegger confrontation, which can be found here: religiousstudies.stanford.edu/thomas-sheeh...
His annotations reveal confusion, surprise, and disappointment. On the page following Heidegger’s dedication, Husserl wrote in Latin: “Plato is a friend, but truth is a greater friend”.
Heidegger dedicated _Being and Time_ to Husserl “in friendship and admiration” and presented Husserl with a bound copy around the time of his 68th birthday. As Husserl read the book he became increasingly aware of the distance between them. 1/3
