Machine Learning | Perceptronai

Intelligence is not just about knowing everything, but also realizing that there is always something new to learn.

Beyond Unimodal: Embracing Multimodal Deep Learning for Enhanced AI

Multimodal deep learning is a subfield of machine learning that combines multiple sources of data to gain understanding.

Beyond Unimodal: Embracing Multimodal Deep Learning for Enhanced AI

Multimodal deep learning is a subfield of machine learning that combines multiple sources of data to gain understanding.

Understanding CLIP

The reason why CLIP is so effective in zero-shot learning is because of the contrastive learning approach to jointly train a neural network.

Leveraging Reasoning-Modulated Representations for MRI and CT scan: A case study

Reasoning-modulated representations aim to create AI systems that are not just data-driven, but also capable of understanding and reasoning.

NAS + Reinforcement learning: A review

Neural architecture search (NAS) is a method for automatically discovering the best neural network architecture for a given task.

Perplexity in AI and Humans

Perplexity is a useful metric to evaluate models in Natural Language Processing (NLP).

Attention Probabilistic U-net

A new hybrid method to find anomalies in CT scans (on-going experiment) Image classification is not new to us and the same stands true...

Artificial intelligence for designing new materials

Understanding the material helps us to understand the working of the universe.

Cost-efficient method to predict 3D hemodynamics

The deep learning methods are inexpensive compare to modeling a cardiovascular hemodynamic system.

Human-Machine Intelligence

The human brain is an amazing biological organ that dictates a human's life altogether right from the time the person is born to death.