اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLSTM: A Search Space Odyssey
388
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful fANOVA framework. In total, we summarize the results of 5400 experimental runs ($approx 15$ years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
قيم البحث
اقرأ أيضاً
Much sequential data exhibits highly non-uniform information distribution. This cannot be correctly modeled by traditional Long Short-Term Memory (LSTM). To address that, recent works have extended LSTM by adding more activations between adjacent inp
uts. However, the approaches often use a fixed depth, which is at the step of the most information content. This one-size-fits-all worst-case approach is not satisfactory, because when little information is distributed to some steps, shallow structures can achieve faster convergence and consume less computation resource. In this paper, we develop a Depth-Adaptive Long Short-Term Memory (DA-LSTM) architecture, which can dynamically adjust the structure depending on information distribution without prior knowledge. Experimental results on real-world datasets show that DA-LSTM costs much less computation resource and substantially reduce convergence time by $41.78%$ and $46.01 %$, compared with Stacked LSTM and Deep Transition LSTM, respectively.
In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach progressively simplifies the original search space by dropping unpromisin
g candidates, thus can reduce difficulties for existing NAS methods to find superior architectures. In particular, we propose an angle-based metric to guide the shrinking process. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed metric is more stable and accurate than accuracy-based and magnitude-based metrics to predict the capability of child models. We also show that the angle-based metric can converge fast while training supernet, enabling us to get promising shrunk search spaces efficiently. ABS can easily apply to most of NAS approaches (e.g. SPOS, FairNAS, ProxylessNAS, DARTS and PDARTS). Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.
We present our new advanced model for population synthesis of close-by cooling NSs. Detailed treatment of the initial spatial distribution of NS progenitors and a detailed ISM structure up to 3 kpc give us an opportunity to discuss the strategy to lo
ok for new isolated cooling NSs. Our main results in this respect are the following: new candidates are expected to be identified behind the Gould Belt, in directions to rich OB associations, in particular in the Cygnus-Cepheus region; new candidates, on average, are expected to be hotter than the known population of cooling NS. Besides the usual approach (looking for soft X-ray sources), the search in empty $gamma$-ray error boxes or among run-away OB stars may yield new X-ray thermally emitting NS candidates.
Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes (and edges) f
ollow no absolute order, and it is hard for traditional machine learning (ML) algorithms to recognize a pattern and generalize their predictions on this type of data. Graph Neural Networks (GNN) successfully tackled this problem. They became popular after the generalization of the convolution concept to the graph domain. However, they possess a large number of hyperparameters and their design and optimization is currently hand-made, based on heuristics or empirical intuition. Neural Architecture Search (NAS) methods appear as an interesting solution to this problem. In this direction, this paper compares two NAS methods for optimizing GNN: one based on reinforcement learning and a second based on evolutionary algorithms. Results consider 7 datasets over two search spaces and show that both methods obtain similar accuracies to a random search, raising the question of how many of the search space dimensions are actually relevant to the problem.
Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is available in
stead. This arises when an approximate gradient is easier to compute than the full gradient (e.g. in meta-learning or unrolled optimization), or when a true gradient is intractable and is replaced with a surrogate (e.g. in certain reinforcement learning applications, or when using synthetic gradients). We propose Guided Evolutionary Strategies, a method for optimally using surrogate gradient directions along with random search. We define a search distribution for evolutionary strategies that is elongated along a guiding subspace spanned by the surrogate gradients. This allows us to estimate a descent direction which can then be passed to a first-order optimizer. We analytically and numerically characterize the tradeoffs that result from tuning how strongly the search distribution is stretched along the guiding subspace, and we use this to derive a setting of the hyperparameters that works well across problems. Finally, we apply our method to example problems, demonstrating an improvement over both standard evolutionary strategies and first-order methods (that directly follow the surrogate gradient). We provide a demo of Guided ES at https://github.com/brain-research/guided-evolutionary-strategies
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
