Pinned Repositories
adversaries_to_convnext
Adversarial examples to the new ConvNeXt architecture
adversaries_to_OOD_detection
dissect-git-re-basin
Replicating and dissecting the git-re-basin project in one-click-replication Colabs
exploring_the_limits_of_OOD_detection
Code to replicate the key results from Exploring the Limits of Out-of-Distribution Detection (https://arxiv.org/abs/2106.03004) by Stanislav Fort, Jie Ren, Balaji Lakshminarayanan, published at NeurIPS 2021.
gaussian-prototypical-networks
Gaussian prototypical network architecture for few-shot learning
hilbert-curves
Generating 3D Hilbert curves
multi-attacks
Replicating the basic adversarial multi-attack experimental results
OpenAI_CLIP_adversarial_examples
Developing adversarial examples and showing their semantic generalization for the OpenAI CLIP model (https://github.com/openai/CLIP)
slice-dice-optimize
Code to replicate the key findings of the paper /What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries/
ulam-spiral
The Ulam prime spiral generator
stanislavfort's Repositories
stanislavfort/exploring_the_limits_of_OOD_detection
Code to replicate the key results from Exploring the Limits of Out-of-Distribution Detection (https://arxiv.org/abs/2106.03004) by Stanislav Fort, Jie Ren, Balaji Lakshminarayanan, published at NeurIPS 2021.
stanislavfort/gaussian-prototypical-networks
Gaussian prototypical network architecture for few-shot learning
stanislavfort/dissect-git-re-basin
Replicating and dissecting the git-re-basin project in one-click-replication Colabs
stanislavfort/OpenAI_CLIP_adversarial_examples
Developing adversarial examples and showing their semantic generalization for the OpenAI CLIP model (https://github.com/openai/CLIP)
stanislavfort/adversaries_to_convnext
Adversarial examples to the new ConvNeXt architecture
stanislavfort/adversaries_to_OOD_detection
stanislavfort/multi-attacks
Replicating the basic adversarial multi-attack experimental results
stanislavfort/ulam-spiral
The Ulam prime spiral generator
stanislavfort/hilbert-curves
Generating 3D Hilbert curves
stanislavfort/slice-dice-optimize
Code to replicate the key findings of the paper /What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries/
stanislavfort/Data-Visualization
A collection of tips and tricks for data visualization in Python.
stanislavfort/ensemble-landscape-cuts
Reproducing plots and loss landscape cuts from the paper *Deep Ensembles: A Loss Landscape Perspective* (https://arxiv.org/abs/1912.02757)
stanislavfort/markov_language_model
A character-level probabilistic language generator based on Markov chains
stanislavfort/singular-value-modified-training-for-fun
Training DNNs on data with singular values removed / kept, testing on similarly modified test sets
stanislavfort/classical_implementation_grovers_algorithm
A classical (non-quantum) implementation of the Grover's algorithm (quantum)
stanislavfort/deepPylos
Deep reinforcement learning for the board game Pylos
stanislavfort/GettingStarted
...with git and GitHub
stanislavfort/initialization-optimum-connectivity-experiments
Assorted experiments to verify the connectivity of DNN initializations to optima in the weight space
stanislavfort/fast_template
A template for really easy blogging with GitHub Pages
stanislavfort/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
stanislavfort/stanislavfort.github.io
A research blog on machine learning, artificial intelligence and physics
stanislavfort/vision_transformer
stanislavfort/BootCamp
Annual computing Boot Camp for new (and other) KIPAC members
stanislavfort/LLM-for-images
An example of a large language model finetuning on MNIST and CIFAR-10
stanislavfort/making-byteformer-work
Trying to make the Apple Byteformer work
stanislavfort/resume
Software developer resume in Latex
stanislavfort/tensorflow
Computation using data flow graphs for scalable machine learning