Filtering by
- All Subjects: deep learning
- Creators: Computer Science and Engineering Program
- Creators: Chakrabarti, Chaitali
- Status: Published
To overcome these challenges, recent works have extensively investigated model compression techniques such as element-wise sparsity, structured sparsity and quantization. While most of these works have applied these compression techniques in isolation, there have been very few studies on application of quantization and structured sparsity together on a DNN model.
This thesis co-optimizes structured sparsity and quantization constraints on DNN models during training. Specifically, it obtains optimal setting of 2-bit weight and 2-bit activation coupled with 4X structured compression by performing combined exploration of quantization and structured compression settings. The optimal DNN model achieves 50X weight memory reduction compared to floating-point uncompressed DNN. This memory saving is significant since applying only structured sparsity constraints achieves 2X memory savings and only quantization constraints achieves 16X memory savings. The algorithm has been validated on both high and low capacity DNNs and on wide-sparse and deep-sparse DNN models. Experiments demonstrated that deep-sparse DNN outperforms shallow-dense DNN with varying level of memory savings depending on DNN precision and sparsity levels. This work further proposed a Pareto-optimal approach to systematically extract optimal DNN models from a huge set of sparse and dense DNN models. The resulting 11 optimal designs were further evaluated by considering overall DNN memory which includes activation memory and weight memory. It was found that there is only a small change in the memory footprint of the optimal designs corresponding to the low sparsity DNNs. However, activation memory cannot be ignored for high sparsity DNNs.
Deep neural networks are composed of multiple layers that are compute/memory intensive. This makes it difficult to execute these algorithms real-time with low power consumption using existing general purpose computers. In this work, we propose hardware accelerators for a traditional AI algorithm based on random forest trees and two representative deep convolutional neural networks (AlexNet and VGG). With the proposed acceleration techniques, ~ 30x performance improvement was achieved compared to CPU for random forest trees. For deep CNNS, we demonstrate that much higher performance can be achieved with architecture space exploration using any optimization algorithms with system level performance and area models for hardware primitives as inputs and goal of minimizing latency with given resource constraints. With this method, ~30GOPs performance was achieved for Stratix V FPGA boards.
Hardware acceleration of DL algorithms alone is not always the most ecient way and sucient to achieve desired performance. There is a huge headroom available for performance improvement provided the algorithms are designed keeping in mind the hardware limitations and bottlenecks. This work achieves hardware-software co-optimization for Non-Maximal Suppression (NMS) algorithm. Using the proposed algorithmic changes and hardware architecture
With CMOS scaling coming to an end and increasing memory bandwidth bottlenecks, CMOS based system might not scale enough to accommodate requirements of more complicated and deeper neural networks in future. In this work, we explore RRAM crossbars and arrays as compact, high performing and energy efficient alternative to CMOS accelerators for deep learning training and inference. We propose and implement RRAM periphery read and write circuits and achieved ~3000x performance improvement in online dictionary learning compared to CPU.
This work also examines the realistic RRAM devices and their non-idealities. We do an in-depth study of the effects of RRAM non-idealities on inference accuracy when a pretrained model is mapped to RRAM based accelerators. To mitigate this issue, we propose Random Sparse Adaptation (RSA), a novel scheme aimed at tuning the model to take care of the faults of the RRAM array on which it is mapped. Our proposed method can achieve inference accuracy much higher than what traditional Read-Verify-Write (R-V-W) method could achieve. RSA can also recover lost inference accuracy 100x ~ 1000x faster compared to R-V-W. Using 32-bit high precision RSA cells, we achieved ~10% higher accuracy using fautly RRAM arrays compared to what can be achieved by mapping a deep network to an 32 level RRAM array with no variations.
In this work, we first use capsule network for overlapping digit recognition problem. We evaluate the performance of the network with respect to recognition accuracy, convergence and training time per epoch. We show that capsule network achieves higher accuracy when training set size is small. When training set size is larger, capsule network and conventional CNN have comparable recognition accuracy. The training time per epoch for capsule network is longer than conventional CNN because of the dynamic routing algorithm. An analysis of the GPU timing shows that adjusting the capsule structure can help decrease the time complexity of the dynamic routing algorithm significantly.
Next, we design a capsule network for speech recognition, specifically, overlapping word recognition. We use both capsule network and conventional CNN to recognize 2 overlapping words in speech files created from 5 word classes. We show that capsule network achieves a considerably higher recognition accuracy (96.92%) compared to conventional CNN (85.19%). Our results show that capsule network recognizes overlapping word by recognizing each individual word in the speech. We also verify the scalability of capsule network by increasing the number of word classes from 5 to 10. Capsule network still shows a high recognition accuracy of 95.42% in case of 10 words while the accuracy of conventional CNN decreases sharply to 73.18%.
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
This thesis attempts to explain Everettian quantum mechanics from the ground up, such that those with little to no experience in quantum physics can understand it. First, we introduce the history of quantum theory, and some concepts that make up the framework of quantum physics. Through these concepts, we reveal why interpretations are necessary to map the quantum world onto our classical world. We then introduce the Copenhagen interpretation, and how many-worlds differs from it. From there, we dive into the concepts of entanglement and decoherence, explaining how worlds branch in an Everettian universe, and how an Everettian universe can appear as our classical observed world. From there, we attempt to answer common questions about many-worlds and discuss whether there are philosophical ramifications to believing such a theory. Finally, we look at whether the many-worlds interpretation can be proven, and why one might choose to believe it.
The purpose of this paper is to provide an analysis of entanglement and the particular problems it poses for some physicists. In addition to looking at the history of entanglement and non-locality, this paper will use the Bell Test as a means for demonstrating how entanglement works, which measures the behavior of electrons whose combined internal angular momentum is zero. This paper will go over Dr. Bell's famous inequality, which shows why the process of entanglement cannot be explained by traditional means of local processes. Entanglement will be viewed initially through the Copenhagen Interpretation, but this paper will also look at two particular models of quantum mechanics, de-Broglie Bohm theory and Everett's Many-Worlds Interpretation, and observe how they explain the behavior of spin and entangled particles compared to the Copenhagen Interpretation.
Breast cancer is one of the most common types of cancer worldwide. Early detection and diagnosis are crucial for improving the chances of successful treatment and survival. In this thesis, many different machine learning algorithms were evaluated and compared to predict breast cancer malignancy from diagnostic features extracted from digitized images of breast tissue samples, called fine-needle aspirates. Breast cancer diagnosis typically involves a combination of mammography, ultrasound, and biopsy. However, machine learning algorithms can assist in the detection and diagnosis of breast cancer by analyzing large amounts of data and identifying patterns that may not be discernible to the human eye. By using these algorithms, healthcare professionals can potentially detect breast cancer at an earlier stage, leading to more effective treatment and better patient outcomes. The results showed that the gradient boosting classifier performed the best, achieving an accuracy of 96% on the test set. This indicates that this algorithm can be a useful tool for healthcare professionals in the early detection and diagnosis of breast cancer, potentially leading to improved patient outcomes.
This research paper explores the effects of data variance on the quality of Artificial Intelligence image generation models and the impact on a viewer's perception of the generated images. The study examines how the quality and accuracy of the images produced by these models are influenced by factors such as size, labeling, and format of the training data. The findings suggest that reducing the training dataset size can lead to a decrease in image coherence, indicating that AI models get worse as the training dataset gets smaller. Moreover, the study makes surprising discoveries regarding AI image generation models that are trained on highly varied datasets. In addition, the study involves a survey in which people were asked to rate the subjective realism of the generated images on a scale ranging from 1 to 5 as well as sorting the images into their respective classes. The findings of this study emphasize the importance of considering dataset variance and size as a critical aspect of improving image generation models as well as the implications of using AI technology in the future.