Artificial Intelligence
Data Mining
Toolkits
Research
- AIF360: The AI Fairness 360 toolkit is an extensible open-source library containg techniques developed by the research community to help detect and mitigate bias in machine learning models throughout the AI application lifecycle.
- AIX360: Explainability 360 toolkit is an open-source library that supports interpretability and explainability of datasets and machine learning models (ProtoDash, Contrastive Explanations, ProfWeight, Monotonicity).
- CausalML: a suite of uplift modeling and causal inference methods using machine learning algorithms based on recent research: Conditional Average Treatment Effect (CATE) or Individual Treatment Effect (ITE).
- XAI Resources: Interesting resources related to XAI (Explainable Artificial Intelligence)
- dopamine: a research framework for fast prototyping of reinforcement learning algorithms
- baselines: high-quality implementations of reinforcement learning algorithms
- : A large-scale dataset of both raw MRI measurements and clinical MRI images.
Production
- Pachyderm: data versioning and pipelines for MLOps
- kubeflow: ML deployments on kubernetes (combine multiple tech, like serving through kserve, use s3 to store artefacts used between ETL, can run notebook, etc)
- deepops: encapsulates best practices in the deployment of GPU server clusters and sharing single powerful nodes
- ollama: Get up and running with Llama 2 and other large language models locally
Documentation
Key People
Articles
- Predict the risk to develop Alzheimer using brain images & deep neural network article / research paper
- Awesome cheat sheet about data science tools link
- New AI research makes it easier to create fake live footage of someone speaking article - video - project
- Notes represent a complete, stand alone interpretation of Stanford's machine learning course presented by Professor Andrew Ng
- Berkeley article for maximum entropy deep reinforcement learning
- PPO: new class of reinforcement learning algorithms, Proximal Policy Optimization, see research paper
- How to build your own AlphaZero AI using Python and Keras
- CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
- Interesting discussion about how visualize high dimensional data link
- Tour of Evaluation Metrics for Imbalanced Classification - summary cheat sheet
- Hyper-parameter optimization algorithms: a short review
- Hyperparameter optimization for Neural Networks
- Neural Networks Demystified
- Emerging Architectures for LLM Applications
Videos
Notions
- Anscombe's quartet
- Quantum machine learning
- ONNX: is an open format to represent deep learning models.
Misc
Quotes
Inside the Moonshot Effort to Finally Figure Out the Brain
To build a dog detector, you need to show the program thousands of things that are dogs and thousands that aren’t dogs,” he says. “My daughter only had to see one dog”—and has happily pointed out puppies ever since. [...] MICrONS researchers are attempting to chart the function and structure of every detail in a small piece of rodent cortex. [...] today’s neural networks are based on a decades-old architecture and a fairly simplistic notion of how the brain works. Essentially, these systems spread knowledge across thousands of densely interconnected “nodes,” analogous to the brain’s neurons. The systems improve their performance by adjusting the strength of the connections. But in most computer neural networks the signals always cascade forward, from one set of nodes to the next. The real brain is full of feedback: for every bundle of nerve fibers conveying signals from one region to the next, there is an equal or greater number of fibers coming back the other way. But why? Are those feedback fibers the secret to one-shot learning and so many other aspects of the brain’s immense power? Is something else going on? [...] The first step is to look into the rats’ brains and figure out what neurons in that cubic millimeter are actually doing. When the animal is given a specific visual stimulus, such as a line oriented a certain way, which neurons suddenly start firing off impulses, and which neighbors respond? [...] Many of today’s AI applications don’t use feedback. Electronic signals in most neural networks cascade from one layer of nodes to the next, but generally not backward. (Don’t be thrown by the term “backpropagation,” which is a way to train neural networks.) That’s not a hard-and-fast rule: “recurrent” neural networks do have connections that go backward, which helps them deal with inputs that change with time. But none of them use feedback on anything like the brain’s scale. In one well-studied part of the visual cortex, says Tai Sing Lee at Carnegie Mellon, “only 5 to 10 percent of the synapses are listening to input from the eyes.” The rest are listening to feedback from higher levels in the brain.