22 citations · 81 across the 31 of their papers we have counts for
35 papers
A Human-in-the-Loop Framework for Efficient Prompt Selection in Microscopy Vision-Language Models
Abhiram Kandiyana, Ankur Mali, Lawrence O. Hall +2
Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality ground truth for training.…
Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
Theophilus Amaefuna, Hitesh Vaidya, Anshuman Chhabra +1
Layer-wise capacity in large language models is highly non-uniform: some layers contribute disproportionately to loss reduction, whereas others are nearly redundant. Existing layer…
Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks
Ankur Mali, Tommaso Salvatori, Alexander Ororbia
Energy-based learning algorithms, such as predictive coding (PC), have garnered significant attention in the machine learning community due to their theoretical properties, such as…
Precision, Stability, and Generalization: A Comprehensive Assessment of RNNs learnability capability for Classifying Counter and Dyck Languages
Neisarg Dave, Daniel Kifer, Lee Giles +1
This study investigates the learnability of Recurrent Neural Networks (RNNs) in classifying structured formal languages, focusing on counter and Dyck languages. Traditionally, both…
A Unified Framework for Continual Learning and Unlearning
Romit Chatterjee, Vikram Chundawat, Ayush Tarun +2
Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately. Continual learning focuses on adapting to new knowledge while…
Investigating Symbolic Capabilities of Large Language Models
Neisarg Dave, Daniel Kifer, C. Lee Giles +1
Prompting techniques have significantly enhanced the capabilities of Large Language Models (LLMs) across various complex tasks, including reasoning, planning, and solving math word…
Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps
Hitesh Vaidya, Travis Desell, Ankur Mali +1
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 t…
A Review of Neuroscience-Inspired Machine Learning
Alexander Ororbia, Ankur Mali, Adam Kohan +2
One major criticism of deep learning centers around the biological implausibility of the credit assignment schema used for learning -- backpropagation of errors. This implausibilit…
Stable and Robust Deep Learning By Hyperbolic Tangent Exponential Linear Unit (TeLU)
Alfredo Fernandez, Ankur Mali
In this paper, we introduce the Hyperbolic Tangent Exponential Linear Unit (TeLU), a novel neural network activation function, represented as . TeLU is de…
Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network
Neisarg Dave, Daniel Kifer, C. Lee Giles +1
This paper analyzes two competing rule extraction methodologies: quantization and equivalence query. We trained RNN models, extracting DFA with a quantization approa…
On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks
Ankur Mali, Alexander Ororbia, Daniel Kifer +1
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 t…
On the Tensor Representation and Algebraic Homomorphism of the Neural State Turing Machine
Ankur Mali, Alexander Ororbia, Daniel Kifer +1
Recurrent neural networks (RNNs) and transformers have been shown to be Turing-complete, but this result assumes infinite precision in their hidden representations, positional enco…
Brain-inspired Computational Intelligence via Predictive Coding
Tommaso Salvatori, Ankur Mali, Christopher L. Buckley +4
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 t…
The Predictive Forward-Forward Algorithm
Alexander Ororbia, Ankur Mali
We propose the predictive forward-forward (PFF) algorithm for conducting credit assignment in neural systems. Specifically, we design a novel, dynamic recurrent neural system that…
Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images
Alexander Ororbia, Ankur Mali
In this work, we develop convolutional neural generative coding (Conv-NGC), a generalization of predictive coding to the case of convolution/deconvolution-based computation. Specif…
Like a bilingual baby: The advantage of visually grounding a bilingual language model
Khai-Nguyen Nguyen, Zixin Tang, Ankur Mali +1
Unlike most neural language models, humans learn language in a rich, multi-sensory and, often, multi-lingual environment. Current language models typically fail to fully capture th…
Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems
Alexander Ororbia, Ankur Mali
In this article, we propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC), designing an a…
A Robust Backpropagation-Free Framework for Images
Timothy Zee, Alexander G. Ororbia, Ankur Mali +1
While current deep learning algorithms have been successful for a wide variety of artificial intelligence (AI) tasks, including those involving structured image data, they present…
Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder
Ankur Mali, Alexander Ororbia, Daniel Kifer +1
Recent advances in deep learning have led to superhuman performance across a variety of applications. Recently, these methods have been successfully employed to improve the rate-di…
An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systems
Ankur Mali, Alexander Ororbia, Daniel Kifer +1
Recent advances in deep learning have resulted in image compression algorithms that outperform JPEG and JPEG 2000 on the standard Kodak benchmark. However, they are slow to train (…
Backprop-Free Reinforcement Learning with Active Neural Generative Coding
Alexander Ororbia, Ankur Mali
In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts w…
OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
Shivansh Rao, Vikas Kumar, Daniel Kifer +2
Given a single RGB panorama, the goal of 3D layout reconstruction is to estimate the room layout by predicting the corners, floor boundary, and ceiling boundary. A common approach…
Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units
Ankur Mali, Alexander Ororbia, Daniel Kifer +1
Automated mathematical reasoning is a challenging problem that requires an agent to learn algebraic patterns that contain long-range dependencies. Two particular tasks that test th…
A provably stable neural network Turing Machine
John Stogin, Ankur Mali, C Lee Giles
We introduce a neural stack architecture, including a differentiable parametrized stack operator that approximates stack push and pop operations for suitable choices of parameters…