Machine Learning Research
What a Molecule’s Structure Reveals: Baidu Creates AI to Classify Molecular Properties
The authors trained a modified GNN on a dataset of 18 million molecules to find molecular properties.
Machine Learning Research
Machine Learning Research
Taming Spurious Correlations: New Technique Helps AI Avoid Classification Mistakes
When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
Machine Learning Research
Ensemble Models Simplified: New Machine Learning Research Simplifies Ensembles
A CLIP model whose weights were the mean of an ensemble of fine-tuned models performed as well as the ensemble and better than its best-performing constituent.
Machine Learning Research
Protein Families Deciphered: Machine Learning Categorizes Proteins Based on Their Functions
Convolutional neural networks separate proteins into functional families without considering their shapes.
Machine Learning Research
Choose the Right Annotators: Jury-Learning Helps Remove Bias from NLP Models
A new machine learning method attempts to account for biases that may be held by certain subsets of labelers.
Machine Learning Research
Learning From Metadata: Descriptive Text Improves Performance for AI Image Classification Systems
Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.
Machine Learning Research
Humanized Training for Robot Arms: New Research Improves Robot Performance and Adaptability
Robots trained via reinforcement learning usually study videos of robots performing the task at hand. A new approach used videos of humans to pre-train robotic arms.
Machine Learning Research
Tradeoffs for Higher Accuracy: Data Augmentation Plus Weight Decay can Boost Some AI Models
Vision models can be improved by training them on several altered versions of the same image and also by encouraging their weights to be close to zero. Recent research showed that both can have adverse effects that may be difficult to detect.
Machine Learning Research
Who Was That Masked Input? Pretraining Method Improves Computer Vision Performance
Researchers have shown that it’s possible to train a computer vision model effectively on around 66 percent of the pixels in each training image. New work used 25 percent, saving computation and boosting performance to boot.
Machine Learning Research
A Transformer for Graphs: New Method for Processing Graph Data with Transformers
Transformers can learn a lot from sequential data like words in a book, but they’ve shown limited ability to learn from data in the form of a graph. A new transformer variant gives graphs due attention.
Machine Learning Research
Pile on the Layers!: DeepNorm Allows Transformers to Accommodate More Layers
Adding layers to a neural network puts the “deep” in deep learning, but it also increases the chance that the network will get stuck during training. A new approach effectively trains transformers with an order of magnitude more layers than previous methods.
Machine Learning Research
Airfoils Automatically Optimized: DeepMind AI Research Simulates Fluid Dynamics
Engineers who design aircraft, aqueducts, and other objects that interact with air and water use numerical simulations to test potential shapes, but they rely on trial and error to improve their designs. A neural simulator can optimize the shape itself.