Crafting effective topic models for brief texts, like tweets and news headlines, is essential for capturing the swift shifts in social dynamics. Traditional topic models, however, often fall short in accurately representing the semantic intricacies of short texts due to their brevity and lack of contextual data. In our study, we harness the advanced capabilities of Large Language Models (LLMs) to introduce a novel approach termed "Topic Refinement". This approach does not directly involve itself in the initial modeling of topics but focuses on improving topics after they have been mined. By employing prompt engineering, we direct LLMs to eliminate off-topic words within a given topic, ensuring that only contextually relevant words are preserved or substituted with ones that fit better semantically. This method emulates human-like scrutiny and improvement of topics, thereby elevating the semantic quality of the topics generated by various models. Our comprehensive evaluation across three unique datasets has shown that our topic refinement approach significantly enhances the semantic coherence of topics.
Understanding neural dynamics is a central topic in machine learning, non-linear physics and neuroscience. However, the dynamics is non-linear, stochastic and particularly non-gradient, i.e., the driving force can not be written as gradient of a potential. These features make analytic studies very challenging. The common tool is to use path integral approach or dynamical mean-field theory, but the drawback is one has to solve the integro-differential or dynamical mean-field equations, which is computationally expensive and has no closed form solutions in general. From the aspect of associated Fokker-Planck equation, the steady state solution is generally unknown. Here, we treat searching for the steady state as an optimization problem, and construct an approximate potential closely related to the speed of the dynamics, and find that searching for the ground state of this potential is equivalent to running a stochastic gradient dynamics. The resultant stationary state follows exactly the canonical Boltzmann measure. Within this framework, the quenched disorder intrinsic in the neural networks can be averaged out by applying the replica method. Our theory reproduces the well-known result of edge-of-chaos, and further the order parameters characterizing the continuous transition are derived, and different scaling behavior with respect to inverse temperature in both sides of the transition is also revealed. Our method opens the door to analytically study the steady state landscape of the deterministic or stochastic high dimensional dynamics.
Spiking neural networks play an important role in brain-like neuromorphic computations and in studying working mechanisms of neural circuits. One drawback of training a large scale spiking neural network is that an expensive cost of updating all weights is required. Furthermore, after training, all information related to the computational task is hidden into the weight matrix, prohibiting us from a transparent understanding of circuit mechanisms. Therefore, in this work, we address these challenges by proposing a spiking mode-based training protocol. The first advantage is that the weight is interpreted by input and output modes and their associated scores characterizing importance of each decomposition term. The number of modes is thus adjustable, allowing more degrees of freedom for modeling the experimental data. This reduces a sizable training cost because of significantly reduced space complexity for learning. The second advantage is that one can project the high dimensional neural activity in the ambient space onto the mode space which is typically of a low dimension, e.g., a few modes are sufficient to capture the shape of the underlying neural manifolds. We analyze our framework in two computational tasks -- digit classification and selective sensory integration tasks. Our work thus derives a mode-based learning rule for spiking neural networks.
Large language models based on self-attention mechanisms have achieved astonishing performances not only in natural language itself, but also in a variety of tasks of different nature. However, regarding processing language, our human brain may not operate using the same principle. Then, a debate is established on the connection between brain computation and artificial self-supervision adopted in large language models. One of most influential hypothesis in brain computation is the predictive coding framework, which proposes to minimize the prediction error by local learning. However, the role of predictive coding and the associated credit assignment in language processing remains unknown. Here, we propose a mean-field learning model within the predictive coding framework, assuming that the synaptic weight of each connection follows a spike and slab distribution, and only the distribution is trained. This meta predictive learning is successfully validated on classifying handwritten digits where pixels are input to the network in sequence, and on the toy and real language corpus. Our model reveals that most of the connections become deterministic after learning, while the output connections have a higher level of variability. The performance of the resulting network ensemble changes continuously with data load, further improving with more training data, in analogy with the emergent behavior of large language models. Therefore, our model provides a starting point to investigate the physics and biology correspondences of the language processing and the unexpected general intelligence.
The recently released artificial intelligence conversational agent, ChatGPT, has gained significant attention in academia and real life. A multitude of early ChatGPT users eagerly explore its capabilities and share their opinions on it via social media. Both user queries and social media posts express public concerns regarding this advanced dialogue system. To mine public concerns about ChatGPT, a novel Self-Supervised neural Topic Model (SSTM), which formalizes topic modeling as a representation learning procedure, is proposed in this paper. Extensive experiments have been conducted on Twitter posts about ChatGPT and queries asked by ChatGPT users. And experimental results demonstrate that the proposed approach could extract higher quality public concerns with improved interpretability and diversity, surpassing the performance of state-of-the-art approaches.
A good theory of mathematical beauty is more practical than any current observation, as new predictions of physical reality can be verified self-consistently. This belief applies to the current status of understanding deep neural networks including large language models and even the biological intelligence. Toy models provide a metaphor of physical reality, allowing mathematically formulating that reality (i.e., the so-called theory), which can be updated as more conjectures are justified or refuted. One does not need to pack all details into a model, but rather, more abstract models are constructed, as complex systems like brains or deep networks have many sloppy dimensions but much less stiff dimensions that strongly impact macroscopic observables. This kind of bottom-up mechanistic modeling is still promising in the modern era of understanding the natural or artificial intelligence. Here, we shed light on eight challenges in developing theory of intelligence following this theoretical paradigm.
Dynamical mean-field theory is a powerful physics tool used to analyze the typical behavior of neural networks, where neurons can be recurrently connected, or multiple layers of neurons can be stacked. However, it is not easy for beginners to access the essence of this tool and the underlying physics. Here, we give a pedagogical introduction of this method in a particular example of generic random neural networks, where neurons are randomly and fully connected by correlated synapses and therefore the network exhibits rich emergent collective dynamics. We also review related past and recent important works applying this tool. In addition, a physically transparent and alternative method, namely the dynamical cavity method, is also introduced to derive exactly the same results. The numerical implementation of solving the integro-differential mean-field equations is also detailed, with an illustration of exploring the fluctuation dissipation theorem.
An obstacle to artificial general intelligence is set by the continual learning of multiple tasks of different nature. Recently, various heuristic tricks, both from machine learning and from neuroscience angles, were proposed, but they lack a unified theory ground. Here, we focus on the continual learning in single-layered and multi-layered neural networks of binary weights. A variational Bayesian learning setting is thus proposed, where the neural network is trained in a field-space, rather than the gradient-ill-defined discrete-weight space, and furthermore, the weight uncertainty is naturally incorporated, and modulates the synaptic resources among tasks. From a physics perspective, we translate the variational continual learning into the Franz-Parisi thermodynamic potential framework, where the previous task knowledge acts as a prior and a reference as well. Therefore, the learning performance can be analytically studied with mean-field order parameters, whose predictions coincide with the numerical experiments using stochastic gradient descent methods. Our proposed principled frameworks also connect to elastic weight consolidation, and neuroscience inspired metaplasticity, providing a theory-grounded method for the real-world multi-task learning with deep networks.
Neural networks with recurrent asymmetric couplings are important to understand how episodic memories are encoded in the brain. Here, we integrate the experimental observation of wide synaptic integration window into our model of sequence retrieval in the continuous time dynamics. The model with non-normal neuron-interactions is theoretically studied by deriving a random matrix theory of the Jacobian matrix in neural dynamics. The spectra bears several distinct features, such as breaking rotational symmetry about the origin, and the emergence of nested voids within the spectrum boundary. The spectral density is thus highly non-uniformly distributed in the complex plane. The random matrix theory also predicts a transition to chaos. In particular, the edge of chaos provides computational benefits for the sequential retrieval of memories. Our work provides a systematic study of time-lagged correlations with arbitrary time delays, and thus can inspire future studies of a broad class of memory models, and even big data analysis of biological time series.