I aim to base my values and behaviour on data: a data-base (pun intended) for how I view and act in this world.

In a parallel to Maslow’s hierarchy of needs, I propose a hierarchy of updating beliefs: from behaviour-driven foundations, through value-driven attitudes, to a data-driven peak. Each layer forms beliefs. Only the top one can revise them on the evidence.

Our models of memory are quietly rounding everything to the nearest integer.

We experience our own working memory as a fluid, continuous stream. We can hold a specific hue of colour, the pitch of a sound, or a precise spatial angle in our mind’s eye for seconds at a time without it snapping to a pre-defined category — though the psychophysics is less flattering than the introspection, and there is a substantial literature on categorical bias showing that human working memory drifts toward category prototypes too. Yet, when we attempt to train standard artificial recurrent neural networks (RNNs) to hold a continuous variable, they stubbornly refuse to maintain this fluidity. Instead of maintaining a smooth, continuous spectrum (what dynamical systems theorists call a continuous attractor), they shatter the state space into discrete, isolated point attractors.

So the continuity we assume our networks have is not something they were ever caught delivering. It is something we expected of them, and the checking has only recently caught up.

“We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters.”

— Yun et al., 2026

It is tempting to think of the primary visual cortex (V1) as a deterministic feature extractor. Light hits the retina, spikes travel down the optic nerve, and V1 meticulously catalogues edges, orientations, and spatial frequencies. Yet, visual perception is fundamentally an act of inference. When faced with an occluded object or a dimly lit scene, the brain does not simply freeze; it actively reconstructs. This process requires dealing with ambiguity, filling in the gaps with prior expectations.

For a long time, standard feedforward artificial neural networks struggled to capture this generative aspect of biological vision. They provided excellent classifications but poor reconstructions under extreme noise. But recently, a specific class of generative machine learning — diffusion models — has shown an uncanny ability to denoise and construct coherent images from pure static. A recent preprint by Yun, Belsten, Bi, Kadkhodaie, Chen, and Olshausen (2026) [1] offers a substantive, testable hypothesis: the recurrent dynamics of V1 can be understood as a minimal diffusion model. It is a genuinely exciting development. It is also more complicated than that™.

A central question in computational neuroscience is how the brain solves the credit assignment problem. How do individual synapses determine how to adjust their strengths based only on locally available information to improve a global objective? In a recent preprint, Safaai, Richards, and Sabatini (2026) demonstrate that exact gradients in conductance-based dendritic networks can be mathematically factorised into a local eligibility term and a non-local compartment error term. That factorisation reframes local learning as a credit-signal approximation problem, and it puts the biophysics inside the gradient rather than alongside it — dendritic geometry and synaptic conductance turn out to be terms in the credit calculation, not context around it. The paper then tests a natural follow-on hypothesis (that shunting inhibition reshapes the error field to suit the feedback a neuron can actually receive) and does not find general support for it. Both halves of that are worth the read.

By treating pyramidal neurons as three-compartment systems — where sensory input, expected value, and error are spatially separated — Lv and colleagues recently demonstrated that multilayer neural networks can be trained without a global error signal, reaching 97.57% on MNIST against backpropagation’s 98.62% while never computing one.

Just one more prompt.

I have said it to myself, and less forgivably out loud to my wife, more times this year than I would like to count. One more prompt and the draft is done. One more and the bug is gone. One more and the figure is finally, actually right. I am never intentionally lying when I say it. I am just, reliably, wrong.

This appeared as the introduction to the Deep Learning Indaba’s newsletter Satu Yetu Our Voice, in November 2024 and appears as a blog post on their website.

Ubuntu is ubiquitous for me as an African, and an avid Linux user. Broadly a philosophy of humanity and connectedness [1], I often see the term used as a self-evident truth or mantra of appreciation for a community. Yet, for this cherished and connected Indaba community, I want to reach beyond appreciation and attempt a touch of understanding our Ubuntu.

Good teaching has always been adaptive.

Creation used to be the hard part.

We provide four guiding principles that are concise, actionable, and will help make organising an inclusive academic event a piece of CAKE 🎂:

• Connectivity: Is everyone seen?
• Adaptability: Is everyone themselves?
• Kinship: Does everyone feel like they belong?
• Empowerment: Can everyone (and the community) grow?

• Github repo
• Paper