Главная
Study mode:
on
You
History
Saved
In progress 0 courses
compleat 0 courses
#Art & Design #Adobe #ChatGPT #GitHub

#Inductive Bias

Showing: 16 courses
Massachusetts Institute of Technology

MIT EI Seminar - Phillip Isola - Emergent Intelligence- Getting More Out of Agents Than You Bake In

0 rewiews
Explore emergent intelligence in AI through unsupervised learning, generative modeling, and self-assembling agents. Discover surprising outcomes beyond explicit programming in representation, video generation, and creature development.
Add to list
38 Lesons
58 minutes
On-Demand
Free-Video
Simons Institute

Human and Machine Inductive Biases for Compositional Linguistic Generalization

0 rewiews
Explore compositional linguistic generalization in humans and artificial neural networks. Compare model results with human patterns, highlighting challenges and opportunities in structural generalization research.
Add to list
1 Lesons
1 hour
On-Demand
Free-Video
Georgia Tech Research

Do We Really Need All That Data? Learning and Control for Contact-rich Manipulation

0 rewiews
Explore data efficiency in robotic manipulation, focusing on contact-driven aspects and implicit learning techniques for improved adaptability and real-time multi-contact MPC deployment.
Add to list
1 Lesons
1 hour 3 minutes
On-Demand
Free-Video
Yannic Kilcher

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

0 rewiews
Explores challenges in unsupervised learning of disentangled representations, questioning assumptions and efficacy of current approaches through theoretical analysis and extensive experiments.
Add to list
6 Lesons
28 minutes
On-Demand
Free-Video
Simons Institute

Improved Machine Learning Algorithm for Predicting Ground State Properties

0 rewiews
Efficient ML algorithm predicts ground state properties of quantum systems using geometric locality, requiring minimal data and scaling favorably for large systems.
Add to list
1 Lesons
1 hour 15 minutes
On-Demand
Free-Video
Yannic Kilcher

An Image is Worth 16x16 Words - Transformers for Image Recognition at Scale

0 rewiews
Explore how Transformers outperform CNNs in image recognition, delving into Vision Transformer architecture, experimental results, and implications for AI research.
Add to list
10 Lesons
30 minutes
On-Demand
Free-Video
Yannic Kilcher

Noether Networks - Meta-Learning Useful Conserved Quantities

0 rewiews
Explore Noether Networks: a novel approach to meta-learning conserved quantities in sequential prediction problems, inspired by Noether's theorem and aimed at discovering useful symmetries and inductive biases.
Add to list
10 Lesons
1 hour 9 minutes
On-Demand
Free-Video
HuggingFace

The Future of Natural Language Processing

0 rewiews
Explore transfer learning in NLP, covering model efficiency, generalization, fine-tuning, and inductive biases. Gain insights into current trends and future directions from HuggingFace's science lead.
Add to list
13 Lesons
1 hour 3 minutes
On-Demand
Free-Video
Simons Institute

A Theory for Emergence of Complex Skills in Language Models

0 rewiews
Explores statistical framework linking LLM cross-entropy loss to language skill competence, analyzing scaling laws' implications for efficient learning and emergence of complex abilities.
Add to list
1 Lesons
1 hour 5 minutes
On-Demand
Free-Video
MITCBMM

Beyond Empirical Risk Minimization - The Lessons of Deep Learning

0 rewiews
Explore deep learning's challenge to traditional machine learning wisdom, examining the "double descent" risk curve and how over-parametrized models can generalize well despite perfect training fit.
Add to list
32 Lesons
47 minutes
On-Demand
Free-Video
Simons Institute

Understanding the Robustness of Deep Learning

0 rewiews
Exploring deep learning robustness, transfer learning dynamics, and overparameterization to gain insights into network functioning and improve model reliability under distribution shifts.
Add to list
1 Lesons
1 hour
On-Demand
Free-Video
Simons Institute

Large ML Potentials for Chemistry - Generalization, Inductive Biases, and Error Cancellation

0 rewiews
Explore machine learning potentials in chemistry, focusing on generalization, inductive biases, and error cancellation techniques for improved accuracy and efficiency.
Add to list
1 Lesons
1 hour 1 minute
On-Demand
Free-Video
Valence Labs

Generalization in Diffusion Models from Geometry-Adaptive Harmonic Representation

0 rewiews
Explore generalization in diffusion models through geometry-adaptive harmonic representation. Analyze denoising DNNs, score functions, and inductive biases to understand high-dimensional density learning and optimal basis adaptation.
Add to list
6 Lesons
1 hour 35 minutes
On-Demand
Free-Video
Yannic Kilcher

Discovering Symbolic Models from Deep Learning with Inductive Biases

0 rewiews
Exploring how Graph Neural Networks and symbolic regression can derive accurate symbolic equations from observational data, combining deep learning with physics-inspired inductive biases.
Add to list
14 Lesons
46 minutes
On-Demand
Free-Video
Alan Turing Institute

PirateNets - Physics-Informed Deep Learning with Residual Adaptive Networks

0 rewiews
Explore PirateNets: a novel deep learning architecture for solving PDE-governed problems, offering improved stability and efficiency over traditional physics-informed neural networks.
Add to list
1 Lesons
1 hour 3 minutes
On-Demand
Free-Video
Simons Institute

Understanding Generalization from Pre-training Loss to Downstream Tasks

0 rewiews
Explore the mystery of pre-trained models' effectiveness, examining contrastive loss, embedding spaces, and the roles of inductive bias and optimizers in generalization to downstream tasks.
Add to list
1 Lesons
1 hour 18 minutes
On-Demand
Free-Video