Welcome to Tensors & Quarks
Exploring the cosmos of Physics & the depths of Machine Learning.
Latest Posts
-
The Deepening Layers of Inception: A Journey Through CNN Time
The story of the Inception architecture is one of ingenuity, iteration, and elegance in the field of deep learning. At a time when researchers were obsessed with increasing the depth and complexity of convolutional neural networks (CNNs) to improve accuracy on large-scale visual tasks, Google’s research team asked a different question: How can we go deeper without paying the full computational price? The answer was Inception—a family of architectures that offered a bold new design paradigm, prioritizing both computational efficiency and representational power. From Inception v1 (GoogLeNet) to Inception-ResNet v2, each version brought transformative ideas that would ripple throughout the deep learning community. This post unpacks the entire journey, layer by layer, innovation by innovation.
Read more → -
How ImageNet Taught Machines to See
The Vision Behind the Dataset
In the early 2000s, artificial intelligence was still stumbling in the dark when it came to understanding images. Researchers had built systems that could play chess or perform basic language tasks, but when it came to something a toddler could do—like identifying a cat in a photo—machines struggled. There was a glaring gap between the potential of machine learning and its real-world applications in vision.
Read more → -
The Random Illusion: Why Adversarial Defenses Aren’t as Robust as They Seem
The field of adversarial machine learning is built on a paradox: models that perform impressively on natural data can be shockingly vulnerable to small, human-imperceptible perturbations. These adversarial examples expose a fragility in deep networks that could have serious consequences in security-critical domains like autonomous driving, medical imaging, or biometric authentication. Naturally, defenses against these attacks have been the subject of intense research. Among them, a seemingly simple strategy has gained popularity: random transformations. By applying random, often non-differentiable perturbations to input images—such as resizing, padding, cropping, JPEG compression, or color quantization—these methods hope to break the adversary’s control over the gradients that guide attacks. At first glance, it seems effective. Robust accuracy increases. Attacks fail. But is this robustness genuine?
Read more → -
Block Geometry & Everything-Bagel Neurons: Decoding Polysemanticity
When Neurons Speak in Tongues: Why Polysemanticity Demands a Theory of Capacity
Crack open a modern vision or language model and you’ll run into a curious spectacle: the same unit flares for “cat ears,” “striped shirts,” and “the Eiffel Tower.” This phenomenon—polysemanticity—is more than a party trick. It frustrates attribution, muddies interpretability dashboards, and complicates any safety guarantee that relies on isolating the “terrorism neuron” or “privacy-violation neuron.”
Read more → -
Geometry vs Quantum Damping: Two Roads to a Smooth Big Bang
Imagine rewinding the Universe until every galaxy, atom and photon collapses into a single blinding flash. Is that primal flash a howling chaos or an eerie stillness? In 1979 Roger Penrose wagered on stillness, proposing that the Weyl tensor—the slice of curvature that stores tidal distortions and gravitational waves—was precisely zero at the Big Bang. Four decades later two very different papers revisit his bet. One rewrites Einstein’s equations so the zero-Weyl state drops out of geometry itself; the other unleashes quantum back-reaction that actively damps any distortion away. Which path makes a smooth dawn more believable?
Read more →