Recent experiments have demonstrated that humans and animals typically reason probabilistically about their environment. This ability requires a neural code that represents probability distributions and neural circuits that are capable of implementing the operations of probabilistic inference. The proposed probabilistic population coding (PPC) framework provides a statistically efficient neural representation of probability distributions that is both broadly consistent with physiological measurements and capable of implementing some of the basic operations of probabilistic inference in a biologically plausible way. However, these experiments and the corresponding neural models have largely focused on simple (tractable) probabilistic computations such as cue combination, coordinate transformations, and decision making. As a result it remains unclear how to generalize this framework to more complex probabilistic computations.

Neural networks have become popular due to their versatility and state-of-the-art results in many applications, such as image classification, natural language processing, speech recognition, forecasting, etc. These applications are also used in resource-constrained environments such as embedded devices. In this work, the susceptibility of neural network implementations to reverse engineering is explored on the NVIDIA Jetson Nano microcomputer via side-channel analysis. To this end, an architecture extraction attack is presented. In the attack, 15 popular convolutional neural network architectures (EfficientNets, MobileNets, NasNet, etc.) are implemented on the GPU of Jetson Nano and the electromagnetic radiation of the GPU is analyzed during the inference operation of the neural networks. The results of the analysis show that neural network architectures are easily distinguishable using deep learning-based side-channel analysis.

The free energy principle (FEP), as an encompassing framework and a unified brain theory, has been widely applied to account for various problems in fields such as cognitive science, neuroscience, social interaction, and hermeneutics. As a computational model deeply rooted in math and statistics, FEP posits an optimization problem based on variational Bayes, which is solved either by dynamic programming or expectation maximization in practice. However, there seems to be a bottleneck in extending the FEP to machine learning and implementing such models with neural networks. This paper gives a preliminary attempt at bridging FEP and machine learning, via a classical neural network model, the Helmholtz machine. As a variational machine learning model, the Helmholtz machine is optimized by minimizing its free energy, the same objective as FEP. Although the Helmholtz machine is not temporal, it gives an ideal parallel to the vanilla FEP and the hierarchical model of the brain, under which the active inference and predictive coding could be formulated coherently. Besides a detailed theoretical discussion, the paper also presents a preliminary experiment to validate the hypothesis. By fine-tuning the trained neural network through active inference, the model performance is promoted to accuracy above 99\%. In the meantime, the data distribution is continuously deformed to a salience that conforms to the model representation, as a result of active sampling.

A feedforward layered network implements a mapping required to control an unknown stochastic nonlinear dynamical system. Training is based on a novel approach that combines stochastic approximation ideas with back(cid:173) propagation. The method is applied to control admission into a queueing sys(cid:173) tem operating in a time-varying environment.

This course is about artificial neural networks. Artificial intelligence and machine learning are getting more and more popular nowadays. In the beginning, other techniques such as Support Vector Machines outperformed neural networks, but in the 21st century neural networks again gain popularity. In spite of the slow training procedure, neural networks can be very powerful. In the first part of the course you will learn about the theoretical background of neural networks, later you will learn how to implement them in Python from scratch.

After my teammates and I had completed our implementation of CycleGANs for our Computer Vision class project, we needed GPUs to run the python script containing the tensorflow code. Since we had multiple datasets, we could not run the code using a single dataset on the Blue Waters quota allotted to us and wait for it to get done. We needed more GPUs!!! So, while my teammates were involved in running it on Blue Waters, I decided to give Google Cloud Platform a try. After going through multiple blogs and tutorials to set up GPUs and tensorflow on Google Cloud, I realized that none of them would give me all the details in one place and therefore, I was compelled to write this blog to provide a step by step procedure on how to set up GPUs and tensorflow on Google Cloud Platform from start to finish. So lets get right to it.

Recent experiments have demonstrated that humans and animals typically reason probabilistically about their environment. This ability requires a neural code that represents probability distributions and neural circuits that are capable of implementing the operations of probabilistic inference. The proposed probabilistic population coding (PPC) framework provides a statistically efficient neural representation of probability distributions that is both broadly consistent with physiological measurements and capable of implementing some of the basic operations of probabilistic inference in a biologically plausible way. However, these experiments and the corresponding neural models have largely focused on simple (tractable) probabilistic computations such as cue combination, coordinate transformations, and decision making. As a result it remains unclear how to generalize this framework to more complex probabilistic computations. Here we address this short coming by showing that a very general approximate inference algorithm known as Variational Bayesian Expectation Maximization can be implemented within the linear PPC framework. We apply this approach to a generic problem faced by any given layer of cortex, namely the identification of latent causes of complex mixtures of spikes. We identify a formal equivalent between this spike pattern demixing problem and topic models used for document classification, in particular Latent Dirichlet Allocation (LDA). We then construct a neural network implementation of variational inference and learning for LDA that utilizes a linear PPC. This network relies critically on two non-linear operations: divisive normalization and super-linear facilitation, both of which are ubiquitously observed in neural circuits. We also demonstrate how online learning can be achieved using a variation of Hebb’s rule and describe an extesion of this work which allows us to deal with time varying and correlated latent causes.

A feedforward layered network implements a mapping required to control an unknown stochastic nonlinear dynamical system. Training is based on a novel approach that combines stochastic approximation ideas with backpropagation. The method is applied to control admission into a queueing system operating in a time-varying environment.

A feedforward layered network implements a mapping required to control an unknown stochastic nonlinear dynamical system. Training is based on a novel approach that combines stochastic approximation ideas with backpropagation. The method is applied to control admission into a queueing system operating in a time-varying environment.

A feedforward layered network implements a mapping required to control an unknown stochastic nonlinear dynamical system. Training is based on a novel approach that combines stochastic approximation ideas with backpropagation. Themethod is applied to control admission into a queueing system operating in a time-varying environment.