Guy Lorberbom
YOU?
Author Swipe
View article: Layer Collaboration in the Forward-Forward Algorithm
Layer Collaboration in the Forward-Forward Algorithm Open
Backpropagation, which uses the chain rule, is the de-facto standard algorithm for optimizing neural networks nowadays. Recently, Hinton (2022) proposed the forward-forward algorithm, a promising alternative that optimizes neural nets laye…
View article: Layer Collaboration in the Forward-Forward Algorithm
Layer Collaboration in the Forward-Forward Algorithm Open
Backpropagation, which uses the chain rule, is the de-facto standard algorithm for optimizing neural networks nowadays. Recently, Hinton (2022) proposed the forward-forward algorithm, a promising alternative that optimizes neural nets laye…
View article: Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis
Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis Open
Sequence-to-Sequence Text-to-Speech architectures that directly generate low level acoustic features from phonetic sequences are known to produce natural and expressive speech when provided with adequate amounts of training data. Such syst…
View article: Latent Space Explanation by Intervention
Latent Space Explanation by Intervention Open
The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives predicti…
View article: Latent Space Explanation by Intervention
Latent Space Explanation by Intervention Open
The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives predicti…
View article: Learning Generalized Gumbel-max Causal Mechanisms
Learning Generalized Gumbel-max Causal Mechanisms Open
To perform counterfactual reasoning in Structural Causal Models (SCMs), one needs to know the causal mechanisms, which provide factorizations of conditional distributions into noise sources and deterministic functions mapping realizations …
View article: Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces Open
Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such ran…
View article: Direct Optimization through $\\arg \\max$ for Discrete Variational\n Auto-Encoder
Direct Optimization through $\\arg \\max$ for Discrete Variational\n Auto-Encoder Open
Reparameterization of variational auto-encoders with continuous random\nvariables is an effective method for reducing the variance of their gradient\nestimates. In the discrete case, one can perform reparametrization using the\nGumbel-Max …
View article: Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder
Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder Open
Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max tri…