Warning: file_put_contents(cache/omni_c339b67f09e5867d6cca35a364d48b1f.json): Failed to open stream: Permission denied in /home/moozonian/public_html/classes/BooksResultsProvider.php on line 304
Deep Learning for Forest Species Identification Based on Macroscopic Images
Available on Internet Archive....
View Book →
Text Understanding from Scratch
This article demontrates that we can apply deep learning to text understanding from character-level inputs all the way up to abstract text concepts, using temporal convolutional networks (ConvNets). W...
View Book →
( 1) Yann Le Cun Llama 2 Has Been Ported To The PSP, In Addition To... Facebook
Yann Lecun post about llama2 on psp...
View Book →
Shape, contour, and grouping in computer vision
viii, 345 pages : 24 cm...
View Book →
Verso un'intelligenza autonoma
Saggio monografico sulla proposta teorica di Yann LeCun per un'intelligenza artificiale autonoma. Ricostruisce il programma di LeCun — critica al paradigma autoregressivo, architettura JEPA, Modello...
View Book →
Machine Learning, Revised and Updated Edition
First published in 2021...
View Book →
Deep multi-scale video prediction beyond mean square error
Learning to predict future images from a video sequence involves the construction of an internal representation that models the image evolution accurately, and therefore, to some degree, its content a...
View Book →
Pedestrian Detection with Unsupervised Multi-Stage Feature Learning
Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive resul...
View Book →
Spectral classification using convolutional neural networks
There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (...
View Book →
Rappresentazione, previsione e mondo interno: un’indagine su JEPA e World Models e la strada verso
La presente monografia indaga le architetture JEPA (Joint-Embedding Predictive Architecture) e i World Models come risposta teoricamente fondata ai limiti strutturali del paradigma generativo-preditti...
View Book →
Stacked What-Where Auto-encoders
We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervised ...
View Book →
From Alchemy To Transhumanism Volumen 1
from Alchemy to Transhumanism volumen 1 How to create a human? from Alchemy to Transhumanism a historical analysis of transmutation and forms of intelligence Project by Rodrigo Granda, with the suppor...
View Book →
Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients
Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically re...
View Book →Selected Writings of Bolivar, Volume Two 1823 - 1830
First published in 1951...
View Book →
Singularity of the Hessian in Deep Learning
We look at the eigenvalues of the Hessian of a loss function before and after training. The eigenvalue distribution is seen to be composed of two parts, the bulk which is concentrated around zero, and...
View Book →
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluatio...
View Book →
Advances in neural information processing systems
First published in 2001...
View Book →
The Loss Surfaces of Multilayer Networks
We study the connection between the highly non-convex loss function of a simple model of the fully-connected feed-forward neural network and the Hamiltonian of the spherical spin-glass model under the...
View Book →
Recurrent Orthogonal Networks and Long-Memory Tasks
Although RNNs have been shown to be powerful tools for processing sequential data, finding architectures or optimization strategies that allow them to model very long term dependencies is still an act...
View Book →
Unsupervised Feature Learning from Temporal Data
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We f...
View Book →
Disentangling factors of variation in deep representations using adversarial training
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summa...
View Book →
Very Deep Convolutional Networks for Text Classification
The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the dee...
View Book →