Artem Kirsanov — Channel Summaries
AI-powered summaries of 46 videos about Artem Kirsanov.
46 summaries
How Your Brain Chooses What to Remember
The brain doesn’t just store memories—it actively tags which experiences deserve later consolidation. A key mechanism centers on hippocampal “sharp...
The Most Important Algorithm in Machine Learning
Backpropagation is the shared engine behind modern machine learning: it turns the goal of minimizing prediction error into a practical, efficient...
How I make science animations
Science animations are built from a deliberately mixed toolkit: Python (for mathematically generated visuals), Blender (for true 3D), and Adobe After...
How Your Brain Organizes Information
The brain’s ability to generalize across wildly different situations may depend on a flexible “cognitive map” that organizes both physical space and...
My simple note-taking setup | Zettelkasten in Obsidian | Step-by-step guide
A Zettelkasten workflow can stay genuinely simple by resisting elaborate tagging schemes and letting structure emerge from links. The core claim is...
Wavelets: a mathematical microscope
Wavelet transform is presented as a “mathematical microscope” for signals that are noisy, irregular, and structured at multiple time scales—letting...
The Brain’s Learning Algorithm Isn’t Backpropagation
Backpropagation’s core mechanics clash with how brains can plausibly operate—especially because it needs tightly coordinated, phase-separated...
The Core Equation Of Neuroscience
Neuronal firing can be reduced to a set of coupled differential equations that track how membrane voltage changes as voltage-gated ion channels open...
The Key Equation Behind Probability
Probability thinking—assigning likelihoods rather than single answers—sits at the core of how both brains and machine-learning systems handle...
Building Blocks of Memory in the Brain
Memory is stored as physical “engram” changes in specific neuron ensembles, and those ensembles can be tagged, reactivated, and even manipulated to...
Generative Model That Won 2024 Nobel Prize
Boltzmann machines turned neural networks from rigid “energy minimizers” into probabilistic generators by injecting randomness into both inference...
Neural manifolds - The Geometry of Behaviour
Neural activity across populations of neurons doesn’t wander through a high-dimensional space at random. Instead, the firing-rate patterns trace out...
A Brain-Inspired Algorithm For Memory
A brain-inspired memory system can retrieve stored information without searching through an astronomically large space of possibilities by turning...
Dendrites: Why Biological Neurons Are Deep Neural Networks
Biological neurons—especially their dendrites—are far more than simple “wires” that sum inputs. Voltage-gated ion channels and dendritic...
Brain Criticality - Optimizing Neural Computations
The core claim behind “brain criticality” is that neural networks operate near a second-order phase transition—an edge-of-instability regime where...
Can We Build an Artificial Hippocampus?
Artificial hippocampus–style intelligence hinges on a simple but powerful idea: learn to predict the next sensory event by factoring experience into...
Logarithmic nature of the brain 💡
Neuronal firing rates don’t cluster like a classic bell curve; they follow a log-normal distribution—an outcome that falls out naturally when...
Brain’s Hidden Learning Limits
Learning can feel limitless—until a new skill refuses to click. A Nature Neuroscience study highlighted in this transcript argues that the bottleneck...
A Universal Theory of Brain Function
A universal theory of brain function frames perception as an ongoing act of hypothesis testing: the brain predicts what caused incoming sensory...
What Textbooks Don't Tell You About Curve Fitting
Linear regression’s familiar “minimize squared vertical errors” rule isn’t just a convenient math trick—it drops out of a probabilistic assumption...
Self-study computational neuroscience | Coding, Textbooks, Math
Computational neuroscience is best understood as a practical pipeline for turning messy brain data—and simplified mathematical models—into testable...
Differential Equations: The Language of Change
Neurons behave less like simple input-output switches and more like time-dependent dynamical systems whose current response depends on their past....
Zettelkasten workflow for research papers | Zotero & Obsidian link
A research workflow built around Zotero plus Obsidian turns scattered PDFs and citations into a connected system of “literature notes” that can later...
Your Brain Is 150,000 Mini-Brains
The neocortex may work less like a patchwork of specialized brain regions and more like a single repeating computation: thousands of “mini-brains”...
Understanding note-taking | Zettelkasten
Zettelkasten’s core promise is simple: turn a flood of information into a living network of ideas that you can actually retrieve, recombine, and...
Your brain is moving along the surface of the torus 🤯
Grid cells in the entorhinal cortex don’t just provide a “sense of direction” for navigation—they generate a low-dimensional geometric structure that...
A Surprising Way Your Brain Is Wired
Small-world network architecture—high local clustering paired with short global path lengths—offers a practical blueprint for how brains (and many...
Theta rhythm: A Memory Clock
Theta rhythm is a hippocampal “memory clock” that coordinates when groups of neurons fire so the brain can bind experience into unified episodes and...
Why Different Neuron Parts Learn Differently?
Synaptic plasticity isn’t governed by a single “one-size-fits-all” learning rule. In the motor cortex of learning mice, the same pyramidal neuron...
Why Two Identical Neurons Behave Differently
Two neurons that look identical can behave very differently because their electrical activity depends on where their state sits in an internal...
Place cells: How your brain creates maps of abstract spaces
Hippocampal “place cells” don’t just light up when an animal is somewhere—they can be manipulated to change behavior, providing direct evidence that...
How AI Solves the Impossible Search Problem
AI and brains both face the same core problem: making accurate inferences when the world is only partially observed. Variational inference tackles...
Memory Consolidation: Time Machine of the Brain
Sleep is doing more than restoring the body: it actively strengthens memories by running a kind of internal “time travel” inside the brain. The core...
My university note-taking | Zettelkasten & more
Conventional university note-taking—furiously copying lectures word for word—often fails at its supposed job: helping students learn and remember....
My Strategy To Consume Information Effectively
Effective reading isn’t about hitting a quota of books; it’s about deciding what’s worth your time and then extracting usable understanding from it....
How to choose a note-taking app | Zettelkasten | Notion vs Roam vs Obsidian
Choosing a note-taking app for Zettelkasten isn’t about finding a “perfect” tool—it’s about avoiding a future trap. The central recommendation is to...
How to read papers effectively | Research reading technique
Reading research papers effectively hinges on one idea: treat each paper like a targeted problem-solving task, not like a book to be consumed from...
The Modular Architecture of Intelligence
Biological brains may learn new tasks fast because they reuse stable “modules” of neural computation—then dynamically route and gate information...
How to Effectively Teach Yourself ANYTHING
Self-directed learning works best when it’s treated like a planned expedition rather than a random browsing session. The core message is that “proper...
A Map of Social Space in Your Brain
A growing body of neuroscience suggests the hippocampus—long known for building maps of physical space—also helps build “social maps,” letting brains...
Mind mapping tutorial for students | Tips & Software
Mind maps work because they translate information from the straight-line format of reading and lectures into the brain’s more natural, branching...
Interleaving vs Spaced repetition | Study hacks
Interleaving—mixing different types of practice problems instead of batching them by topic—can substantially raise learning performance, sometimes...
Your brain CAN'T Multitask - Here's why
Multitasking fails not because the brain lacks willpower, but because attention is a limited, costly resource—and every switch leaves behind...
How to overcome study procrastination | 3 powerful tips
Procrastination isn’t mainly a character flaw—it’s a brain response to discomfort. When a task feels difficult, pointless, or unclear, the mind...
How to focus when studying from home
Staying focused at home comes down to building an “attention state” before work starts, then protecting it with friction against distractions. The...
All RNNs Come From This One Idea
Most neural networks are “amnesic”: they process each input as if it were new, with no built-in sense of time. That limitation becomes obvious when...