Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus on specific input parts. The softmax unit, which is a key part of the attention mechanism, normalizes the attention scores. Hence, the performance of LLMs in various NLP tasks depends significantly on the crucial role played by the attention mechanism with the softmax unit.In-context learning is one of the celebrated abilities of recent LLMs. Without further parameter updates, Transformers can learn to predict based on few in-context examples. However, the reason why Transformers becomes in-context learners is not well understood.Recently, in-context learning has been studied from a mathematical perspective with simplified linear self-attention without softmax unit. Based on a linear regression formulation $\min_x\| Ax - b \|_2$, existing works show linear Transformers' capability of learning linear functions in context. The capability of Transformers with softmax unit approaching full Transformers, however, remains unexplored.In this work, we study the in-context learning based on a softmax regression formulation $\min_{x} \| \langle \exp(Ax), {\bf 1}_n \rangle^{-1} \exp(Ax) - b \|_2$. We show the upper bounds of the data transformations induced by a single self-attention layer with softmax unit and by gradient-descent on a $\ell_2$ regression loss for softmax prediction function.Our theoretical results imply that when training self-attention-only Transformers for fundamental regression tasks, the models learned by gradient-descent and Transformers show great similarity.

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related tasks.

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus on specific input parts. The softmax unit, which is a key part of the attention mechanism, normalizes the attention scores. Hence, the performance of LLMs in various NLP tasks depends significantly on the crucial role played by the attention mechanism with the softmax unit.In-context learning is one of the celebrated abilities of recent LLMs. Without further parameter updates, Transformers can learn to predict based on few in-context examples.

We introduce HD (or "Hierarchical-Deep") models, a new compositional learning architecture that integrates deep learning models with structured hierarchical Bayesian models. Specifically we show how we can learn a hierarchical Dirichlet process (HDP) prior over the activities of the top-level features in a Deep Boltzmann Machine (DBM). This compound HDP-DBM model learns to learn novel concepts from very few training examples, by learning low-level generic features, high-level features that capture correlations among low-level features, and a category hierarchy for sharing priors over the high-level features that are typical of different kinds of concepts. We present efficient learning and inference algorithms for the HDP-DBM model and show that it is able to learn new concepts from very few examples on CIFAR-100 object recognition, handwritten character recognition, and human motion capture datasets.

Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as softmax and GELU (Gaussion Error Linear Unit) that are accelerated directly in hardware. Currently, function evaluation is done separately for each function and rarely allows for hardware reuse. To mitigate this problem, in this work, we map the computation of GELU to a softmax operator. In this way, the efficient hardware units designed already for softmax can be reused for computing GELU as well. Computation of GELU can enjoy the inherent vectorized nature of softmax and produce in parallel multiple GELU outcomes. Experimental results show that computing GELU via a pre-existing and incrementally modified softmax hardware unit (a) does not reduce the accuracy of representative NLP applications and (b) allows the reduction of the overall hardware area and power by 6.1% and 11.9%, respectively, on average.

After reading François Chollet's wonderful book Deep Learning with Python I became curious about the different neural network architectures and which one is the best for various tasks. I had already thought of getting some practice with word data so I decided to take on the project of classifying the language that a word is written in. The first direction that I think of when working with words is to use recurrent neural networks. Chollet's book also suggests that a series of 1D convolutions could be appropriate. Finally, I found a nice blog post that achieved a similar task using a simple fully connected network. This was the best opportunity to try each of these nice networks on the same project!

This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architecture in which the weights for the unknown and known categories are jointly optimised. Second, an unsupervised method is used for further tuning the weights. Sharing weights injects prior knowledge to unknown categories. The unsupervised tuning (i.e. the risk minimisation) improves the F-Measure when recognising nearly zero-shot data on the DSTC3 corpus. This unsupervised method can be applied subject to two assumptions: the rank of the class marginal is assumed to be known and the class-conditional scores of the classifier are assumed to follow a Gaussian distribution.

We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents. We overcome the apparent difficulty of training a DBM with judicious parameter tying. This parameter tying enables an efficient pretraining algorithm and a state initialization scheme that aids inference. The model can be trained just as efficiently as a standard Restricted Boltzmann Machine. Our experiments show that the model assigns better log probability to unseen data than the Replicated Softmax model. Features extracted from our model outperform LDA, Replicated Softmax, and DocNADE models on document retrieval and document classification tasks.

We introduce HD (or ``Hierarchical-Deep'') models, a new compositional learning architecture that integrates deep learning models with structured hierarchical Bayesian models. Specifically we show how we can learn a hierarchical Dirichlet process (HDP) prior over the activities of the top-level features in a Deep Boltzmann Machine (DBM). This compound HDP-DBM model learns to learn novel concepts from very few training examples, by learning low-level generic features, high-level features that capture correlations among low-level features, and a category hierarchy for sharing priors over the high-level features that are typical of different kinds of concepts. We present efficient learning and inference algorithms for the HDP-DBM model and show that it is able to learn new concepts from very few examples on CIFAR-100 object recognition, handwritten character recognition, and human motion capture datasets.