Deep Learning (Article)

R0:6c8a4ce33496b8be6ac636aa4dfd0fef-Proving and Improving the Platonic Representation Hypothesis with JEPAs

Proving and Improving the Platonic Representation Hypothesis with JEPAs

Can a compact text encoder learn representations that agree with vision more closely than those of a much larger language model? This preprint investigates that question through a conditional mathematical theorem and experiments comparing Joint-Embedding Predictive Architectures (JEPAs) with next-token prediction. Its central proposal is to train on different descriptions of the same scene, encouraging models to preserve shared information. A 109-million-parameter text JEPA achieves stronger visual alignment than the evaluated language models, including models with up to 72 billion parameters. The reported gains concern representation geometry, retrieval and selected classification tasks. The paper also combines a JEPA with an LLM decoder to generate image descriptions. This publication examines those contributions alongside the assumptions of the theorem, the meaning of the reported sample-efficiency advantage, the role of generated training captions and the limits of comparisons with general-purpose language models. The findings suggest a practical direction for representation learning while leaving broader claims about reasoning, planning and autonomous world models open.

Proving and Improving the Platonic Representation Hypothesis with JEPAs Leer más »

R0:36cbb300eb0fca3fc0ffa717d93011b5-Explainable deep learning improves human mental models of self-driving cars

Explainable deep learning improves human mental models of self-driving cars

How can a passenger understand why a self-driving car behaves unexpectedly? This study introduces the Concept-Wrapper Network (CW-Net), which connects a learned planner to human-readable concepts and examines whether explanations improve understanding of vehicle behaviour. Its evaluation combines private-track experiments with a real autonomous vehicle, expert and non-expert studies, and an online study using public-road recordings collected while a human drove. Participants receiving concept explanations performed better on selected questions about surprising situations. The accompanying critique distinguishes the architecture in which concepts determine the planning reward from an alternative that provides diagnostic explanations without determining trajectory selection. It also examines concept-recognition errors, the inclusion of caution questions in a prediction measure, and uncertainty about effects during ordinary situations. The publication offers evidence about interpretable planning and human understanding, while explaining why these results do not establish safer autonomous operation on public roads or unrestricted replication of the complete vehicle system.

Explainable deep learning improves human mental models of self-driving cars Leer más »

R0:c4c3ffc882452ee50fea21d2c6b1486a-CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization

CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization

CNN Explainer tightly integrates a model overview that summarizes a CNN’s structure, and on-demand, dynamic visual explanation views that help users understand the underlying components of CNNs. Through smooth transitions across levels of abstraction, our tool enables users to inspect the interplay between low-level mathematical operations and high-level model structures.

CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization Leer más »

R0:a8fc240769ba4448b373719f7fbe640d-Do Vision Transformers See Like Convolutional Neural Networks?

Do Vision Transformers See Like Convolutional Neural Networks?

Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more uniform representations across all layers. We explore how these differences arise, finding crucial roles played by self-attention, which enables early aggregation of global information, and ViT residual connections, which strongly propagate features from lower to higher layers.

Do Vision Transformers See Like Convolutional Neural Networks? Leer más »

S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training

S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training

We introduce S++, a simple, robust, and deployable framework for training a neural network (NN) using private data from multiple sources, using secret-shared secure function evaluation. In short, consider a virtual third party to whom every data-holder sends their inputs, and which computes the neural network: in our case, this virtual third party is actually a set of servers which individually learn nothing, even with a malicious (but non-colluding) adversary.

S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training Leer más »

R0:daa46e0033d013818bcc056d269d5737-Unsupervised deep clustering and reinforcement learning can accurately segment MRI brain tumors with very small training sets

Unsupervised deep clustering and reinforcement learning can accurately segment MRI brain tumors with very small training sets

«We have demonstrated a proof-of-principle application of unsupervised deep clustering and reinforcement learning to segment brain tumors. The approach represents human-allied AI that requires minimal input from the radiologist without the need for hand-traced annotation».

Unsupervised deep clustering and reinforcement learning can accurately segment MRI brain tumors with very small training sets Leer más »

R0identifier_ 7029b309b114bdb1aa72b6fd0da905f3-Yann LeCun’s Deep Learning Course at CDS

Yann LeCun’s Deep Learning Course at CDS

This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. The prerequisites include: DS-GA 1001 Intro to Data Science or a graduate-level machine learning course.

Yann LeCun’s Deep Learning Course at CDS Leer más »

Medical Open Network for AI (MONAI), AI Toolkit for Healthcare Imaging

Medical Open Network for AI (MONAI), AI Toolkit for Healthcare Imaging

The MONAI framework is the open-source foundation being created by Project MONAI. MONAI is a freely available, community-supported, PyTorch-based framework for deep learning in healthcare imaging. It provides domain-optimized foundational capabilities for developing healthcare imaging training workflows in a native PyTorch paradigm.

Medical Open Network for AI (MONAI), AI Toolkit for Healthcare Imaging Leer más »