I recently came back from the ML4Good Germany Camp 2024 https://www.ml4good.org/. I’m glad I went and here’s why you should too. Gathering The Quest Visit the neighboring AI Safety Covenant for a gathering of Witches and Wizards. What is ML4Good Camp It’s a 10-day in-person camp with a bunch of cool people learning and working on AI safety. We were 25 participants mostly from across Europe, 5 TAs, 3 organizers, and even a cook!

Within the shadowed corridors of knowledge, where the veil between worlds is thin, lies the Deck of Many Prompts—Each card a gateway, a unique portal etched with symbols and glyphs. When drawn by a worthy seeker, the cards whisper secrets of creation, manipulation, and insight, offering glimpses into realms both wondrous and perilous. Yet, beware the capricious nature of the Deck, for its magic is as wild as it is mighty, shaping destinies with the mere flick of a card.

In the hallowed halls of the Arcanum, apprentice quantizers gather around ancient scrolls, their eager hands weaving complex patterns of magic, each fold compressing vast models into the nebulous depths of the Bag of Holding. As they manipulate these arcane energies, the fabric of reality thins, threatening to fray at the edges of their understanding. Those who delve too recklessly into its powers may find their meticulously crafted models reduced to incomprehensible noise, lost in the echoing void of the bag’s mysterious expanse.

Beneath the Arcane Academy, the Crucible of the Magi endures—aglow with a roaring fire, this dark iron relic, used to dissect enchanted artifacts into their primal essences, whispers secrets of raw power and hidden truths as it deconstructs, revealing the core components fundamental to spellcraft. Those who wield its power must tread carefully, for the truths it unveils can be as perilous as they are enlightening. Crucible of the Magi The Quest Harness the power of SVD to compress images and recommend books.

Beneath a weathered cloak, three crafty goblins stand stacked, masquerading as an ancient wizard. Each goblin, akin to the layers of a Recurrent Neural Network. Every action built upon the input of others, warping the delicate weave of mana. Though seamless from the outside, this clever orchestration of individual parts works in mischievous harmony, each decision a product of collective cunning. Three goblins masquerading as a wizard The Quest Look through the archives for ancient magic, and implement the different flavors of recurrent neural networks whose power once reigned supreme and may rise anew to claim their throne.

At first glance, the cloak appears to be nothing more than a collection of rags stitched together haphazardly, frayed edges fluttering like whispers in the wind. Yet, as the old wizard wraps it tightly around his shoulders, the air shimmers with a soft, silvery glow. Each tattered piece of fabric is imbued with arcane runes, barely visible, that hum with ancient magic, shielding him from the piercing cold and prying eyes alike.

In the ethereal dance of the cosmos, where the arcane whispers intertwine with the silent echoes of unseen dimensions, the Ioun Stone of Mastery emerges as a beacon of unparalleled prowess. This luminescent orb, orbiting its bearer’s head, is a testament to the mastery of both magical and mathematical realms, offering a bridge between the manipulation of arcane energies and the intricate ballet of tensor mathematics. As the stone orbits, it casts a subtle glow, its presence a constant reminder of the dual dominion it grants over the spellbinding complexities of magic and the abstract elegance of multidimensional calculations, making the wielder a maestro of both mystical incantations and the unseen algebra of the universe.

Veiled in a mist of arcane energy, the Orb of Scrying rests silently upon its ancient pedestal. Crafted from crystal as clear as mountain spring water, it waits for the touch of a seer. To the untrained eye, it’s merely a beautiful artifact, but to a wielder of magic, it’s a window to the unseen. Whispering the old words, the mage’s eyes lock onto the orb’s depths. Visions swirl within, revealing secrets hidden across lands and time, as the orb bridges the gap between the known and the unknown.

In the dimly lit chambers of his ancient library, the wizard Eldron carefully weaves his spell over a complex array of arcane symbols. With each precise gesture, he transmutes these symbols, imbuing them with a hidden layer of meaning: the magic of positional encoding. This enchantment allows the symbols to hold not just the essence of words, but also their place in the grand tapestry of language. Eldron’s eyes gleam with satisfaction as the embeddings shimmer, now ready to reveal their secrets in perfect harmony and sequence.

The Mirror of Life Trapping, a relic of ancient magic, ensnares the souls of those who dare gaze upon its deceptive surface. Within its mystical depths, trapped spirits linger, awaiting release or eternal confinement. Mirror of Life Trapping The Quest Craft a Mirror of Life Trapping. Capture the visual essence of a target. GAN (Generative Adversarial Network) GAN is an architecture merging two different networks competing with each other: Discriminator: wants to predict if the input is real or fake Generator: wants to generate fakes indistinguishable from the real ones GAN Discriminator The discriminator is a simple binary classifier.

Daedalus, master craftsman of ancient myths, conceived the Labyrinth: a maze of bewildering complexity. Its winding paths and endless turns, a testament to his genius, were designed to confine the fearsome Minotaur, blurring the line between architectural marvel and cunning trap. Daedalus designing the labyrinth by DALL-E The Quest Train a network on Daedalus work to generate new mazes. Autoencoder An autoencoder is a type of network shaped like an hourglass.

Born of ancient magic, the Chromatic Chameleon prowls the shadows with scales that pulse and shimmer in a dance of arcane radiance. Its form, a living canvas, shifts through the hues of twilight, an elusive guardian draped in spectral energies. Only those with keen senses may glimpse the majestic, ever-changing creature lurking in the mystic realms. Chromatic Chameleon The Quest Repurpose an image classifier to do style transfer from a donor style image to a receiver content image.

A Beholder awakens. Its myriad eyes, each a facet of mechanistic insight, gaze upon the intricate layers of information, revealing hidden patterns in the dreams of code. In the tapestry of deepdream, the Beholder becomes the guardian of interpretability, its central eye illuminating the enigmatic connections woven within the digital labyrinth. Beauty is in the eye of the Beholder The Quest Produce deepdreams from an image classifier. Try to identify specific features in the network, and alter them to blind the network.

In the dimly lit corridors of the ancient dungeon, where shadows dance and secrets lie in wait, an eerie silence is suddenly shattered by the faint creaking of wooden planks. Unbeknownst to the adventurers, a malevolent presence lurks among the mundane, adopting the guise of an innocuous chest or treasure trove. Beware the mimic, a shape-shifting aberration that hungers for the thrill of deception and the taste of unsuspecting intruders.

Gelatinous Cube The Quest Get a feel for how unsupervised clustering algorithms work and their differences. Unsupervised Clustering A set of algorithms used to identify groups within unlabeled dataset. If we go back to the word embeddings examples, running a clustering algorithm would return groups of words with similar meanings, or sharing a common topic (e.g. [king, queen, prince, princess], [apple, lemon, banana, coconut]). Lets run through a few popular clustering algorithms.

Say hi to our new bestiary friend, Grok. Our lovely ogre: Grok the cruel The Quest Let’s explore how a network can generalize the solution after already reaching perfect loss. Grokking Grokking is the model’s ability to move beyond rote learning of training data and develop a broader understanding that allows it to generalize well to unseen inputs. The Model We’ll try to reproduce this effect using a model trained to predict modular addition (a + b) % vocab.

Adding a new entry to the bestiary, the Minotaur. Minotaur by stable diffusion The Quest As a first step toward Reinforcement Learning (RL) let’s write a maze solver using Deep Q-Network (DQN). Bellman’s Equation To me DQN seems to be the RL technique requiring the least effort. All you need to do is to balance the left side of the Bellman’s equation with its right side: $$Q(s, a) = R + \gamma .

This is the first post going off road for our own little adventure and not following an online course. Today’s quest will consist of slaying a dragon building an intuition for embeddings. The Quest The original idea was to try to reproduce the word arithmetic examples from Google’s Word2Vec demo: King - Man + Woman = Queen and Paris - France + Italy = Rome. (Spoiler alert) it turned out to be more of an experiment on how to create/handle/visualize word embeddings.

A look at episode #7: Let’s build GPT: from scratch, in code, spelled out from Andrej Karpathy amazing tutorial series. For the final episode of the series 😭 we keep all the little things about reading, partitioning and tokenizing the dataset from previous videos. And start a new model from scratch to generate some shakespeare sounding text. The model The model is inspired GPT-2 and the Attention is All You Need paper.

A look at episode #6: The spelled-out intro to language modeling: Building makemore Part 5: Building a WaveNet from Andrej Karpathy amazing tutorial series. Starting from the makemore3 (3-gram character-level MLP model) code as a base. It implements a deepter more structured model (while maintaining roughly the same number of parameters) to improve the loss. Improve the structure of the code The first half of the video focus on bringing more structure to the code.