Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Mali, Ankur A"'
Recent research has seen significant interest in methods for concept removal and targeted forgetting in diffusion models. In this paper, we conduct a comprehensive white-box analysis to expose significant vulnerabilities in existing diffusion model u
Externí odkaz:
http://arxiv.org/abs/2409.05668
Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately. Continual learning focuses on adapting to new knowledge while preserving past information, whereas unlearning involves selectively f
Externí odkaz:
http://arxiv.org/abs/2408.11374
Prompting techniques have significantly enhanced the capabilities of Large Language Models (LLMs) across various complex tasks, including reasoning, planning, and solving math word problems. However, most research has predominantly focused on languag
Externí odkaz:
http://arxiv.org/abs/2405.13209
An intelligent system capable of continual learning is one that can process and extract knowledge from potentially infinitely long streams of pattern vectors. The major challenge that makes crafting such a system difficult is known as catastrophic fo
Externí odkaz:
http://arxiv.org/abs/2402.12465
One major criticism of deep learning centers around the biological implausibility of the credit assignment schema used for learning -- backpropagation of errors. This implausibility translates into practical limitations, spanning scientific fields, i
Externí odkaz:
http://arxiv.org/abs/2403.18929
Autor:
Fernandez, Alfredo, Mali, Ankur
In this paper, we introduce the Hyperbolic Tangent Exponential Linear Unit (TeLU), a novel neural network activation function, represented as $f(x) = x{\cdot}tanh(e^x)$. TeLU is designed to overcome the limitations of conventional activation function
Externí odkaz:
http://arxiv.org/abs/2402.02790
This paper analyzes two competing rule extraction methodologies: quantization and equivalence query. We trained $3600$ RNN models, extracting $18000$ DFA with a quantization approach (k-means and SOM) and $3600$ DFA by equivalence query($L^{*}$) meth
Externí odkaz:
http://arxiv.org/abs/2402.02627
Artificial neural networks (ANNs) with recurrence and self-attention have been shown to be Turing-complete (TC). However, existing work has shown that these ANNs require multiple turns or unbounded computation time, even with unbounded precision in w
Externí odkaz:
http://arxiv.org/abs/2309.14691
Recurrent neural networks (RNNs) and transformers have been shown to be Turing-complete, but this result assumes infinite precision in their hidden representations, positional encodings for transformers, and unbounded computation time in general. In
Externí odkaz:
http://arxiv.org/abs/2309.14690
Autor:
Salvatori, Tommaso, Mali, Ankur, Buckley, Christopher L., Lukasiewicz, Thomas, Rao, Rajesh P. N., Friston, Karl, Ororbia, Alexander
Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century. The majority of results in AI thus far have been achieved using deep neural networks trained with the error backpropagation learning algorithm. However, the
Externí odkaz:
http://arxiv.org/abs/2308.07870