Hamidreza Saghir

A follow-up.

Coding agents write impressive first drafts.

Agent frameworks hide the loop behind agent.run() and a graph DSL.

Offense asks 'does a bug exist?'

Both fit a distribution over outputs conditioned on an input.

From spectral clustering to Gaussian processes to transformer attention, the same primitive, a similarity matrix between points, keeps showing up as the load-bearing piece of very different models.

Back after a long hiatus, what's changed and what's coming.

BFS, Dijkstra, and A* differ by one line: the data structure you pop the next node from.

So PyTorch is the new popular framework for deep learners and many new papers release code in PyTorch that one might want to inspect.

PCA, factor analysis, ICA, Gaussian mixtures, vector quantization, HMMs, and Kalman filters are the same two equations with different restrictions on the latent variables.

Backpropagation, belief propagation, the Viterbi algorithm, and matrix-chain multiplication all solve the same problem: summing over exponentially many paths in a graph by reusing work.

I love the simplicity of autoencoders as a very intuitive unsupervised learning method.

PCA, factor analysis, logistic regression, Gaussian mixtures, HMMs, and Kalman filters are the same probabilistic graphical model with different independence assumptions.

What is a neural network?

I typically use my computers at home to connect to my work computer.

Theano might look intimidating, but there are a few concepts that if understood, would make the engineering involved in deep learning more tangible.

Deep learning is hot!

Barbara Minto's pyramid: put the answer at the top, let the reader's questions drive the hierarchy, and choose deduction or induction at each branch.

I have been blogging about the qualifications of advanced degree holders and how they should be approaching a job search.

Recently, I read a post on the Chronicle where the author had listed all the excuses she could come up with, to justify her decision not to pursue a fulfilling and rewarding…

A PhD has traditionally been the path to a career in academia.

An old note on Elon Musk's first-principles reasoning, updated for 2026.

The world is nonlinear.

One of the most exhilarating observations of physics and mathematics for me, comes from understanding the concept of nonlinearity. i.e. inputs don't necessarily need to be…